A high-level knowledge-representation framework that can be used to solve problems declaratively based on
abductive reasoning. It extends normal
logic programming by allowing some predicates to be incompletely defined, declared as abducible predicates.
A form of
logical inference which starts with an observation or set of observations then seeks to find the simplest and most likely explanation. This process, unlike
deductive reasoning, yields a plausible conclusion but does not
positively verify it.[1] abductive inference,[1] or retroduction[2]
A
mathematical model for
data types, where a data type is defined by its behavior (
semantics) from the point of view of a user of the data, specifically in terms of possible values, possible operations on data of this type, and the behavior of these operations.
The process of removing physical, spatial, or temporal details[3] or
attributes in the study of objects or
systems in order to more closely attend to other details of interest[4]
A perceived increase in the rate of
technological change throughout history, which may suggest faster and more profound change in the future and may or may not be accompanied by equally profound social and cultural change.
An area of machine learning concerned with creation and modification of software agent's knowledge about effects and preconditions of the actions that can be executed within its environment. This knowledge is usually represented in logic-based action description language and used as the input for automated planners.
A way of characterizing the most basic problem of intelligent systems: what to do next. In artificial intelligence and computational cognitive science, "the action selection problem" is typically associated with intelligent agents and animats—artificial systems that exhibit complex behaviour in an agent environment.
Also adaptive network-based fuzzy inference system.
A kind of
artificial neural network that is based on Takagi–Sugeno fuzzy
inference system. The technique was developed in the early 1990s.[6][7] Since it integrates both neural networks and
fuzzy logic principles, it has potential to capture the benefits of both in a single
framework. Its inference system corresponds to a set of fuzzy
IF–THEN rules that have learning capability to approximate nonlinear functions.[8] Hence, ANFIS is considered to be a universal estimator.[9] For using the ANFIS in a more efficient and optimal way, one can use the best parameters obtained by genetic algorithm.[10][11]
In
computer science, specifically in
algorithms related to
pathfinding, a
heuristic function is said to be admissible if it never overestimates the cost of reaching the goal, i.e. the cost it estimates to reach the goal is not higher than the lowest possible cost from the current point in the path.[12]
Also artificial emotional intelligence or emotion AI.
The study and development of systems and devices that can recognize, interpret, process, and simulate human
affects. Affective computing is an interdisciplinary field spanning
computer science,
psychology, and
cognitive science.[13][14]
In the field of artificial intelligence, the most difficult problems are informally known as AI-complete or AI-hard, implying that the difficulty of these computational problems is equivalent to that of solving the central artificial intelligence problem—making computers as intelligent as people, or
strong AI.[18] To call a problem AI-complete reflects an attitude that it would not be solved by a simple specific algorithm.
A property of an
algorithm which relates to the number of
computational resources used by the algorithm. An algorithm must be
analyzed to determine its resource usage, and the efficiency of an algorithm can be measured based on usage of different resources. Algorithmic efficiency can be thought of as analogous to engineering
productivity for a repeating or continuous process.
The determination of the
computational complexity of algorithms, that is the amount of time, storage and/or other resources necessary to
execute them. Usually, this involves determining a
function that relates the length of an algorithm's input to the number of steps it takes (its
time complexity) or the number of storage locations it uses (its
space complexity).
A form of
declarative programming oriented towards difficult (primarily
NP-hard)
search problems. It is based on the
stable model (answer set) semantics of
logic programming. In ASP, search problems are reduced to computing stable models, and answer set solvers—programs for generating stable models—are used to perform search.
A set of subroutine definitions,
communication protocols, and tools for building software. In general terms, it is a set of clearly defined methods of communication among various components. A good API makes it easier to develop a
computer program by providing all the building blocks, which are then put together by the
programmer. An API may be for a web-based system,
operating system,
database system, computer hardware, or
software library.
The technique of finding
strings that match a
pattern approximately (rather than exactly). The problem of approximate string matching is typically divided into two sub-problems: finding approximate
substring matches inside a given string and finding dictionary strings that match the pattern approximately.
A way to deal with contentious information and draw conclusions from it. In an abstract argumentation framework,[24] entry-level information is a set of abstract arguments that, for instance, represent data or a proposition. Conflicts between arguments are represented by a
binary relation on the set of arguments. In concrete terms, you represent an argumentation framework with a
directed graph such that the nodes are the arguments, and the arrows represent the attack relation. There exist some extensions of the Dung's framework, like the logic-based argumentation frameworks[25] or the value-based argumentation frameworks.[26]
A class of computationally intelligent,
rule-based machine learning systems inspired by the principles and processes of the vertebrate
immune system. The algorithms are typically modeled after the immune system's characteristics of
learning and
memory for use in
problem-solving.
Any
intelligence demonstrated by
machines, in contrast to the natural intelligence displayed by humans and other animals. In
computer science, AI research is defined as the study of "
intelligent agents": any device that perceives its environment and takes actions that maximize its chance of successfully achieving its goals.[27] Colloquially, the term "artificial intelligence" is applied when a machine mimics "cognitive" functions that humans associate with other
human minds, such as "learning" and "problem solving".[28]
Artificial neural networks (ANNs), also shortened to neural networks (NNs) or neural nets, are a branch of
machine learning models that are built using principles of neuronal organization discovered by
connectionism in the
biological neural networks constituting animal
brains.[29][30]
An international, nonprofit, scientific society devoted to promote research in, and responsible use of,
artificial intelligence. AAAI also aims to increase public understanding of artificial intelligence (AI), improve the teaching and training of AI practitioners, and provide guidance for research planners and funders concerning the importance and potential of current AI developments and future directions.[31]
Machine learning-based attention is a mechanism mimicking
cognitive attention. It calculates "soft" weights for each word, more precisely for its embedding, in the
context window. It can do it either in parallel (such as in
transformers) or sequentially (such as
recursive neural networks). "Soft" weights can change during each runtime, in contrast to "hard" weights, which are (pre-)trained and fine-tuned and remain frozen afterwards. Multiple attention heads are used in transformer-based
large language models.
A logic and representation system defined by
Ryszard S. Michalski. It combines elements of
predicate logic,
propositional calculus, and
multi-valued logic. Attributional calculus provides a formal language for natural induction, an inductive learning process whose results are in forms natural to people.
An interactive experience of a real-world environment where the objects that reside in the real-world are "augmented" by computer-generated perceptual information, sometimes across multiple sensory modalities, including
visual,
auditory,
haptic,
somatosensory, and
olfactory.[32]
A field of
machine learning which aims to automatically configure a machine learning system to maximize its performance (e.g, classification accuracy).
The
self-managing characteristics of
distributed computing resources, adapting to unpredictable changes while hiding intrinsic complexity to operators and users. Initiated by
IBM in 2001, this initiative ultimately aimed to develop computer systems capable of self-management, to overcome the rapidly growing complexity of computing
systems management, and to reduce the barrier that complexity poses to further growth.[34]
A method used in
artificial neural networks to calculate a gradient that is needed in the calculation of the
weights to be used in the network.[39] Backpropagation is shorthand for "the backward propagation of errors", since an error is computed at the output and distributed backwards throughout the network's layers. It is commonly used to train
deep neural networks,[40] a term referring to neural networks with more than one hidden layer.[41]
In computer vision, the bag-of-words model (BoW model) can be applied to
image classification, by treating
image features as words. In document classification, a
bag of words is a
sparse vector of occurrence counts of words; that is, a sparse
histogram over the vocabulary. In
computer vision, a bag of visual words is a vector of occurrence counts of a vocabulary of local image features.
A technique for improving the performance and stability of
artificial neural networks. It is a technique to provide any layer in a neural network with inputs that are zero mean/unit variance.[48] Batch normalization was introduced in a 2015 paper.[49][50] It is used to normalize the input layer by adjusting and scaling the activations.[51]
A formalism and a methodology for having a technique to specify
probabilistic models and solve problems when less than the necessary information is available.
A population-based
search algorithm which was developed by Pham, Ghanbarzadeh and et al. in 2005.[52] It mimics the food foraging behaviour of honey bee colonies. In its basic version the algorithm performs a kind of neighbourhood search combined with global search, and can be used for both
combinatorial optimization and
continuous optimization. The only condition for the application of the bees algorithm is that some measure of distance between the solutions is defined. The effectiveness and specific abilities of the bees algorithm have been proven in a number of studies.[53][54][55][56]
A
mathematical model of
plan execution used in
computer science,
robotics,
control systems and
video games. They describe switchings between a finite set of tasks in a modular fashion. Their strength comes from their ability to create very complex tasks composed of simple tasks, without worrying how the simple tasks are implemented. BTs present some similarities to
hierarchical state machines with the key difference that the main building block of a behavior is a task rather than a state. Its ease of human understanding make BTs less error-prone and very popular in the game developer community. BTs have shown to generalize several other control architectures.[58][59]
A software model developed for programming
intelligent agents. Superficially characterized by the implementation of an agent's beliefs, desires and intentions, it actually uses these concepts to solve a particular problem in agent programming. In essence, it provides a mechanism for separating the activity of selecting a plan (from a plan library or an external planner application) from the execution of currently active plans. Consequently, BDI agents are able to balance the time spent on deliberating about plans (choosing what to do) and executing those plans (doing it). A third activity, creating the plans in the first place (planning), is not within the scope of the model, and is left to the system designer and programmer.
A mathematical notation that describes the
limiting behavior of a
function when the
argument tends towards a particular value or infinity. It is a member of a family of notations invented by
Paul Bachmann,[61]Edmund Landau,[62] and others, collectively called Bachmann–Landau notation or asymptotic notation.
A
treedata structure in which each node has at most two
children, which are referred to as the left child and the right child. A
recursive definition using just
set theory notions is that a (non-empty) binary tree is a
tuple (L, S, R), where L and R are binary trees or the
empty set and S is a
singleton set.[63] Some authors allow the binary tree to be the empty set as well.[64]
An
artificial intelligence approach based on the
blackboard architectural model,[65][66][67][68] where a common knowledge base, the "blackboard", is iteratively updated by a diverse group of specialist knowledge sources, starting with a problem specification and ending with a solution. Each knowledge source updates the blackboard with a partial solution when its internal constraints match the blackboard state. In this way, the specialists work together to solve the problem.
Also propositional satisfiability problem; abbreviated SATISFIABILITY or SAT.
The problem of determining if there exists an
interpretation that
satisfies a given
Booleanformula. In other words, it asks whether the variables of a given Boolean formula can be consistently replaced by the values TRUE or FALSE in such a way that the formula evaluates to TRUE. If this is the case, the formula is called satisfiable. On the other hand, if no such assignment exists, the function expressed by the formula is
FALSE for all possible variable assignments and the formula is unsatisfiable. For example, the formula "a AND NOT b" is satisfiable because one can find the values a = TRUE and b = FALSE, which make (a AND NOT b) = TRUE. In contrast, "a AND NOT a" is unsatisfiable.
A technology that employs the latest findings in
neuroscience. The term was first introduced by the Artificial Intelligence Laboratory in
Zurich, Switzerland, in the context of the
ROBOY project.[70] Brain Technology can be employed in robots,[71]know-how management systems[72] and any other application with self-learning capabilities. In particular, Brain Technology applications allow the visualization of the underlying learning architecture often coined as "know-how maps".
A very general
problem-solving technique and
algorithmic paradigm that consists of systematically enumerating all possible candidates for the solution and checking whether each candidate satisfies the problem's statement.
A machine learning system that is a type of
artificial neural network (ANN) that can be used to better model hierarchical relationships. The approach is an attempt to more closely mimic biological neural organization.[73]
A field of
robotics that attempts to invoke cloud technologies such as
cloud computing,
cloud storage, and other
Internet technologies centred on the benefits of converged infrastructure and shared services for robotics. When connected to the cloud, robots can benefit from the powerful computation, storage, and communication resources of modern
data center in the cloud, which can process and share information from various robots or agent (other machines, smart objects, humans, etc.). Humans can also delegate tasks to robots remotely through
networks. Cloud computing technologies enable robot systems to be endowed with powerful capability whilst reducing costs through cloud technologies. Thus, it is possible to build lightweight, low cost, smarter robots have intelligent "brain" in the cloud. The "brain" consists of
data center,
knowledge base, task planners,
deep learning, information processing, environment models, communication support, etc.[75][76][77][78]
An incremental system for hierarchical
conceptual clustering. COBWEB was invented by Professor
Douglas H. Fisher, currently at Vanderbilt University.[79][80] COBWEB incrementally organizes observations into a
classification tree. Each node in a classification tree represents a class (concept) and is labeled by a probabilistic concept that summarizes the attribute-value distributions of objects classified under the node. This classification tree can be used to predict missing attributes or the class of a new object.[81]
The
Institute of Creative Technologies defines cognitive architecture as: "hypothesis about the fixed structures that provide a mind, whether in natural or artificial systems, and how they work together – in conjunction with knowledge and skills embodied within the architecture – to yield intelligent behavior in a diversity of complex environments."[82]
In general, the term cognitive computing has been used to refer to new hardware and/or software that
mimics the functioning of the
human brain[83][84][85][86][87][88] and helps to improve human decision-making.[89][90] In this sense, CC is a new type of computing with the goal of more accurate models of how the human brain/
mind senses,
reasons, and responds to stimulus.
A type of
artificial neural network using a
divide and conquer strategy in which the responses of multiple neural networks (experts) are combined into a single response.[93] The combined response of the committee machine is supposed to be superior to those of its constituent experts. Compare
ensembles of classifiers.
In
artificial intelligence research, commonsense knowledge consists of facts about the everyday world, such as "Lemons are sour", that all humans are expected to know. The first AI program to address common sense knowledge was
Advice Taker in 1959 by John McCarthy.[94]
A branch of artificial intelligence concerned with simulating the human ability to make presumptions about the type and essence of ordinary situations they encounter every day.[95]
Focuses on classifying computational problems according to their inherent difficulty, and relating these classes to each other. A computational problem is a task solved by a computer. A computation problem is solvable by mechanical application of mathematical steps, such as an algorithm.
An
interdisciplinary field concerned with the statistical or rule-based modeling of
natural language from a computational perspective, as well as the study of appropriate computational approaches to linguistic questions.
The theory, experimentation, and engineering that form the basis for the design and use of
computers. It involves the study of
algorithms that process, store, and communicate
digitalinformation. A
computer scientist specializes in the theory of computation and the design of computational systems.[117]
In
predictive analytics and
machine learning, the concept drift means that the statistical properties of the target variable, which the model is trying to predict, change over time in unforeseen ways. This causes problems because the predictions become less accurate as time passes.
In the study of
path-finding problems in
artificial intelligence, a
heuristic function is said to be consistent, or monotone, if its estimate is always less than or equal to the estimated distance from any neighboring vertex to the goal, plus the cost of reaching that neighbor.
A
machine learning and inference framework that augments the learning of conditional (probabilistic or discriminative) models with declarative constraints.
A form of
constraint programming, in which
logic programming is extended to include concepts from
constraint satisfaction. A constraint logic program is a logic program that contains constraints in the body of clauses. An example of a clause including a constraint is A(X,Y):-X+Y>0,B(X),C(Y). In this clause, X+Y>0 is a constraint; A(X,Y), B(X), and C(Y) are
literals as in regular logic programming. This clause states one condition under which the statement A(X,Y) holds: X+Y is greater than zero and both B(X) and C(Y) are true.
A language whose
phonology,
grammar, and
vocabulary are consciously devised, instead of having developed
naturally. Constructed languages may also be referred to as artificial, planned, or invented languages.[122]
In
control systems engineering is a subfield of mathematics that deals with the control of continuously operating
dynamical systems in engineered processes and machines. The objective is to develop a control model for controlling such systems using a control action in an optimum manner without delay or overshoot and ensuring control
stability.
In
deep learning, a convolutional neural network (CNN, or ConvNet) is a class of
deep neural networks, most commonly applied to analyzing visual imagery. CNNs use a variation of
multilayer perceptrons designed to require minimal
preprocessing.[123] They are also known as shift invariant or space invariant artificial neural networks (SIANN), based on their shared-weights architecture and
translation invariance characteristics.[124][125]
The Dartmouth Summer Research Project on Artificial Intelligence was the name of a 1956 summer workshop now considered by many[130][131] (though not all[132]) to be the
seminal event for
artificial intelligence as a field.
The process of integrating multiple data sources to produce more consistent, accurate, and useful information than that provided by any individual data source.[133]
The process of combining
data residing in different sources and providing users with a unified view of them.[134] This process becomes significant in a variety of situations, which include both commercial (such as when two similar companies need to merge their
databases) and scientific (combining research results from different
bioinformatics repositories, for example) domains. Data integration appears with increasing frequency as the volume (that is,
big data) and the need to share existing data
explodes.[135] It has become the focus of extensive theoretical work, and numerous open problems remain unsolved.
An interdisciplinary field that uses scientific methods, processes, algorithms and systems to extract
knowledge and insights from
data in various forms, both structured and unstructured,[136][137] similar to
data mining. Data science is a "concept to unify statistics, data analysis, machine learning and their related methods" in order to "understand and analyze actual phenomena" with data.[138] It employs techniques and theories drawn from many fields within the context of
mathematics,
statistics,
information science, and
computer science.
A collection of
data. Most commonly a data set corresponds to the contents of a single
database table, or a single statistical
data matrix, where every
column of the table represents a particular variable, and each
row corresponds to a given member of the data set in question. The data set lists values for each of the variables, such as height and weight of an object, for each member of the data set. Each value is known as a datum. The data set may comprise data for one or more members, corresponding to the number of rows.
A system used for
reporting and
data analysis.[139] DWs are central repositories of integrated data from one or more disparate sources. They store current and historical data in one single place[140]
Aan
information system that supports business or organizational
decision-making activities. DSSs serve the management, operations and planning levels of an organization (usually mid and higher management) and help people make decisions about problems that may be rapidly changing and not easily specified in advance—i.e. unstructured and semi-structured decision problems. Decision support systems can be either fully computerized or human-powered, or a combination of both.
The study of the reasoning underlying an
agent's choices.[142] Decision theory can be broken into two branches:
normative decision theory, which gives advice on how to make the
best decisions given a set of uncertain beliefs and a set of
values, and descriptive decision theory which analyzes how existing, possibly irrational agents actually make decisions.
Uses a
decision tree (as a
predictive model) to go from observations about an item (represented in the branches) to conclusions about the item's target value (represented in the leaves). It is one of the predictive modeling approaches used in
statistics,
data mining and
machine learning.
was a
chess-playing computer developed by
IBM. It is known for being the first computer chess-playing system to win both a chess game and a chess match against a reigning world champion under regular time controls.
A family of formal
knowledge representation languages. Many DLs are more expressive than
propositional logic but less expressive than
first-order logic. In contrast to the latter, the core reasoning problems for DLs are (usually)
decidable, and efficient decision procedures have been designed and implemented for these problems. There are general, spatial, temporal, spatiotemporal, and fuzzy descriptions logics, and each description logic features a different balance between DL expressivity and
reasoningcomplexity by supporting different sets of mathematical constructors.[155]
A scientific field which aims at studying the developmental mechanisms, architectures, and constraints that allow lifelong and open-ended learning of new skills and new knowledge in embodied
machines.
Concerned with the development of algorithms and techniques that are able to determine whether the behaviour of a system is correct. If the system is not functioning correctly, the algorithm should be able to determine, as accurately as possible, which part of the system is failing, and which kind of fault it is facing. The computation is based on observations, which provide information on the current behaviour.
A computer system intended to converse with a human with a coherent structure. Dialogue systems have employed text, speech, graphics, haptics, gestures, and other modes for communication on both the input and output channel.
In
machine learning, diffusion models, also known as diffusion probabilistic models or score-based generative models, are a class of
latent variable models. They are
Markov chains trained using
variational inference.[156] The goal of diffusion models is to learn the latent structure of a dataset by modeling the way in which data points diffuse through the
latent space. In
computer vision, this means that a neural network is trained to
denoise images blurred with
Gaussian noise by learning to reverse the diffusion process.[157][158] It mainly consists of three major components: the forward process, the reverse process, and the sampling procedure.[159] Three examples of generic diffusion modeling frameworks used in computer vision are denoising diffusion probabilistic models, noise conditioned score networks, and stochastic differential equations.[160]
The process of reducing the number of random variables under consideration[161] by obtaining a set of principal variables. It can be divided into
feature selection and
feature extraction.[162]
Any system with a countable number of states. Discrete systems may be contrasted with continuous systems, which may also be called analog systems. A final discrete system is often modeled with a directed
graph and is analyzed for correctness and complexity according to
computational theory. Because discrete systems have a countable number of states, they may be described in precise
mathematical models. A
computer is a
finite state machine that may be viewed as a discrete system. Because computers are often used to model not only other discrete systems but continuous systems as well, methods have been developed to represent real-world continuous systems as discrete systems. One such method involves sampling a continuous signal at
discrete time intervals.
A subfield of
artificial intelligence research dedicated to the development of distributed solutions for problems. DAI is closely related to and a predecessor of the field of
multi-agent systems.[163]
A logical framework dealing with knowledge and information change. Typically, DEL focuses on situations involving multiple
agents and studies how their knowledge changes when
events occur.
A learning method in which the system tries to construct a general, input-independent target function during training of the system, as opposed to
lazy learning, where generalization beyond the training data is delayed until a query is made to the system.[164]
A
recurrent neural network with a sparsely connected hidden layer (with typically 1% connectivity). The connectivity and weights of hidden
neurons are fixed and randomly assigned. The weights of output neurons can be learned so that the network can (re)produce specific temporal patterns. The main interest of this network is that although its behaviour is non-linear, the only weights that are modified during training are for the synapses that connect the hidden neurons to output neurons. Thus, the error function is quadratic with respect to the parameter vector and can be differentiated easily to a linear system.[169][170]
An
intelligent agent that interacts with the environment through a physical body within that environment. Agents that are represented graphically with a body, for example a human or a cartoon animal, are also called embodied agents, although they have only virtual, not physical, embodiment.[171]
An interdisciplinary field of research, the aim of which is to explain the mechanisms underlying intelligent behavior. It comprises three main methodologies: 1) the modeling of psychological and biological systems in a holistic manner that considers the mind and body as a single entity, 2) the formation of a common set of general principles of intelligent behavior, and 3) the experimental use of robotic agents in controlled environments.
In
machine learning, particularly in the creation of
artificial neural networks, ensemble averaging is the process of creating multiple models and combining them to produce a desired output, as opposed to creating just one model.
epoch (machine learning)
In
machine learning, particularly in the creation of
artificial neural networks, an epoch is training the model for one cycle through the full training dataset. Small models are typically trained for as many epochs as it takes to reach the best performance on the validation dataset. The largest models may train for only one epoch.
A computer system that emulates the decision-making ability of a human expert.[176] Expert systems are designed to solve complex problems by
reasoning through bodies of knowledge, represented mainly as
if–then rules rather than through conventional
procedural code.[177]
A type of
classification tree. Fast-and-frugal trees can be used as decision-making tools which operate as lexicographic classifiers, and, if required, associate an action (decision) to each class or category.[178]
In
machine learning,
pattern recognition, and
image processing, feature extraction starts from an initial set of measured data and builds derived values (
features) intended to be informative and non-redundant, facilitating the subsequent learning and generalization steps, and in some cases leading to better human interpretations.
In
machine learning, feature learning or representation learning[144] is a set of techniques that allows a system to automatically discover the representations needed for feature detection or classification from raw data. This replaces manual
feature engineering and allows a machine to both learn the features and use them to perform a specific task.
In
machine learning and
statistics, feature selection, also known as variable selection, attribute selection or variable subset selection, is the process of selecting a subset of relevant
features (variables, predictors) for use in model construction.
A type of machine learning that allows for training on multiple devices with decentralized data, thus helping preserve the privacy of individual users and their data.
Also known as first-order predicate calculus and predicate logic.
A collection of
formal systems used in
mathematics,
philosophy,
linguistics, and
computer science. First-order logic uses
quantified variables over non-logical objects and allows the use of sentences that contain variables, so that rather than propositions such as Socrates is a man one can have expressions in the form "there exists X such that X is
Socrates and X is a man" and there exists is a quantifier while X is a variable.[179] This distinguishes it from
propositional logic, which does not use quantifiers or relations.[180]
A condition that can change over time. In logical approaches to reasoning about actions, fluents can be represented in
first-order logic by
predicates having an argument that depends on time.
One of the two main methods of reasoning when using an
inference engine and can be described
logically as repeated application of modus ponens. Forward chaining is a popular implementation strategy for
expert systems,
businesses and
production rule systems. The opposite of forward chaining is
backward chaining. Forward chaining starts with the available
data and uses inference rules to extract more data (from an end user, for example) until a
goal is reached. An
inference engine using forward chaining searches the inference rules until it finds one where the
antecedent (If clause) is known to be true. When such a rule is found, the engine can conclude, or infer, the
consequent (Then clause), resulting in the addition of new
information to its data.[181]
An artificial intelligence
data structure used to divide
knowledge into substructures by representing "
stereotyped situations". Frames are the primary data structure used in artificial intelligence
frame language.
A technology used for
knowledge representation in artificial intelligence. Frames are stored as
ontologies of
sets and subsets of the
frame concepts. They are similar to class hierarchies in
object-oriented languages although their fundamental design goals are different. Frames are focused on explicit and intuitive representation of knowledge whereas objects focus on
encapsulation and
information hiding. Frames originated in AI research and objects primarily in
software engineering. However, in practice the techniques and capabilities of frame and object-oriented languages overlap significantly.
A hypothetical
artificial general intelligence (AGI) that would have a positive effect on humanity. It is a part of the
ethics of artificial intelligence and is closely related to
machine ethics. While machine ethics is concerned with how an artificially intelligent agent should behave, friendly artificial intelligence research is focused on how to practically bring about this behaviour and ensuring it is adequately constrained.
A
control system based on
fuzzy logic—a
mathematical system that analyzes
analog input values in terms of
logical variables that take on continuous values between 0 and 1, in contrast to classical or
digital logic, which operates on discrete values of either 1 or 0 (true or false, respectively).[184][185]
A simple form for the
many-valued logic, in which the
truth values of variables may have any degree of "Truthfulness" that can be represented by any real number in the range between 0 (as in Completely False) and 1 (as in Completely True) inclusive. Consequently, It is employed to handle the concept of partial truth, where the truth value may range between completely true and completely false. In contrast to
Boolean logic, where the truth values of variables may have the integer values 0 or 1 only.
In classical
set theory, the membership of elements in a set is assessed in binary terms according to a
bivalent condition — an element either belongs or does not belong to the set. By contrast, fuzzy set theory permits the gradual assessment of the membership of elements in a set; this is described with the aid of a
membership function valued in the real unit interval [0, 1]. Fuzzy sets generalize classical sets, since the
indicator functions (aka characteristic functions) of classical sets are special cases of the membership functions of fuzzy sets, if the latter only take values 0 or 1.[186] In fuzzy set theory, classical bivalent sets are usually called
crisp sets. The fuzzy set theory can be used in a wide range of domains in which information is incomplete or imprecise, such as
bioinformatics.[187]
An
operator used in
genetic algorithms to guide the algorithm towards a solution to a given problem. There are three main types of operators (
mutation,
crossover and
selection), which must work in conjunction with one another in order for the algorithm to be successful.
A
large language model based on the
transformer architecture that generates text. It is first pretrained to predict the next
token in texts (a token is typically a word, subword, or punctuation). After their pretraining, GPT models can generate human-like text by repeatedly predicting the token that they would expect to follow. GPT models are usually also fine-tuned, for example with
RLHF to reduce
hallucinations or harmful behaviour, or to format the ouput in a conversationnal format.[197]
In mathematics, and more specifically in
graph theory, a graph is a structure amounting to a set of objects in which some pairs of the objects are in some sense "related". The objects correspond to mathematical abstractions called vertices (also called nodes or points) and each of the related pairs of vertices is called an edge (also called an arc or line).[198]
A
database that uses
graph structures for
semantic queries with
nodes,
edges, and properties to represent and store data. A key concept of the system is the graph (or edge or relationship), which directly relates data items in the store a collection of nodes of data and edges representing the relationships between the nodes. The relationships allow data in the store to be linked together directly, and in many cases retrieved with one operation. Graph databases hold the relationships between data as a priority. Querying relationships within a graph database is fast because they are perpetually stored within the database itself. Relationships can be intuitively visualized using graph databases, making it useful for heavily inter-connected data.[199][200]
The process of visiting (checking and/or updating) each vertex in a
graph. Such traversals are classified by the order in which the vertices are visited.
Tree traversal is a special case of graph traversal.
A technique designed for
solving a problem more quickly when classic methods are too slow, or for finding an approximate solution when classic methods fail to find any exact solution. This is achieved by trading optimality, completeness,
accuracy, or
precision for speed. In a way, it can be considered a shortcut. A heuristic function, also called simply a heuristic, is a
function that ranks alternatives in
search algorithms at each branching step based on available information to decide which branch to follow. For example, it may approximate the exact solution.[201]
A
heuristic search method that seeks to automate the process of selecting, combining, generating, or adapting several simpler heuristics (or components of such heuristics) to efficiently solve computational search problems, often by the incorporation of
machine learning techniques. One of the motivations for studying hyper-heuristics is to build systems which can handle classes of problems rather than solving just one problem.[202][203][204]
A method of
machine learning, in which input data is continuously used to extend the existing model's knowledge i.e. to further train the model. It represents a dynamic technique of
supervised learning and
unsupervised learning that can be applied when training data becomes available gradually over time or its size is out of system memory limits. Algorithms that can facilitate incremental learning are known as incremental machine learning algorithms.
The merging of information from heterogeneous sources with differing conceptual, contextual and typographical representations. It is used in
data mining and consolidation of data from unstructured or semi-structured resources. Typically, information integration refers to textual representations of knowledge but is sometimes applied to
rich-media content. Information fusion, which is a related term, involves the combination of information into a new set of information towards reducing redundancy and uncertainty.[133]
A possible outcome of humanity building
artificial general intelligence (AGI). AGI would be capable of recursive self-improvement leading to rapid emergence of ASI (
artificial superintelligence), the limits of which are unknown, at the time of the technological singularity.
An
autonomous entity which acts, directing its activity towards achieving goals (i.e. it is an
agent), upon an
environment using observation through sensors and consequent actuators (i.e. it is intelligent). Intelligent agents may also
learn or use
knowledge to achieve their goals. They may be very simple or
very complex.
Also virtual assistant or personal digital assistant.
A
software agent that can perform tasks or services for an individual based on verbal commands. Sometimes the term "
chatbot" is used to refer to virtual assistants generally or specifically accessed by
online chat (or in some cases online chat programs that are exclusively for entertainment purposes). Some virtual assistants are able to interpret human speech and respond via synthesized voices. Users can ask their assistants questions, control
home automation devices and media playback via voice, and manage other basic tasks such as email, to-do lists, and calendars with verbal commands.[207]
An
intelligent agent is intrinsically motivated to act if the information content alone, of the experience resulting from the action, is the motivating factor. Information content in this context is measured in the
information theory sense as quantifying uncertainty. A typical intrinsic motivation is to search for unusual (surprising) situations, in contrast to a typical extrinsic motivation such as the search for food. Intrinsically motivated artificial agents display behaviours akin to
exploration and
curiosity.[208]
A graphical breakdown of a question that dissects it into its different components vertically and that progresses into details as it reads to the right.[209]: 47 Issue trees are useful in
problem solving to identify the root causes of a problem as well as to identify its potential solutions. They also provide a reference point to see how each piece fits into the whole picture of a problem.[210]
A well-known
knowledge representation system in the tradition of
semantic networks and
frames; that is, it is a
frame language. The system is an attempt to overcome semantic indistinctness in semantic network representations and to explicitly represent conceptual information as a structured inheritance network.[212][213][214]
The process used to define the rules and ontologies required for a
knowledge-based system. The phrase was first used in conjunction with
expert systems to describe the initial tasks associated with developing an expert system, namely finding and interviewing
domain experts and capturing their knowledge via
rules,
objects, and
frame-basedontologies.
A
computer program that
reasons and uses a
knowledge base to
solvecomplex problems. The term is broad and refers to many different kinds of systems. The one common theme that unites all knowledge based systems is an attempt to represent knowledge explicitly and a
reasoning system that allows it to derive new knowledge. Thus, a knowledge-based system has two distinguishing features: a
knowledge base and an
inference engine.
The creation of
knowledge from structured (
relational databases,
XML) and unstructured (
text, documents,
images) sources. The resulting knowledge needs to be in a machine-readable and machine-interpretable format and must
represent knowledge in a manner that facilitates inferencing. Although it is methodically similar to
information extraction (
NLP) and
ETL (data warehouse), the main criterion is that the extraction result goes beyond the creation of structured information or the transformation into a
relational schema. It requires either the reuse of existing
formal knowledge (reusing identifiers or
ontologies) or the generation of a schema based on the source data.
A computer language designed to enable systems to share and re-use information from
knowledge-based systems. KIF is similar to
frame languages such as
KL-ONE and
LOOM but unlike such language its primary role is not intended as a framework for the expression or use of knowledge but rather for the interchange of knowledge between systems. The designers of KIF likened it to
PostScript. PostScript was not designed primarily as a language to store and manipulate documents but rather as an interchange format for systems and devices to share documents. In the same way KIF is meant to facilitate sharing of knowledge across different systems that use different languages, formalisms, platforms, etc.
A
language model with a large number of parameters (typically at least a billion) that are adjusted during training. Due to its size, it requires a lot of data and computing capability to train. Large language models are usually based on the
transformer architecture.[217]
In
machine learning, lazy learning is a learning method in which generalization of the
training data is, in theory, delayed until a query is made to the system, as opposed to in
eager learning, where the system tries to generalize the training data before receiving queries.
An artificial
recurrent neural network architecture[219] used in the field of
deep learning. Unlike standard
feedforward neural networks, LSTM has feedback connections that make it a "general purpose computer" (that is, it can compute anything that a
Turing machine can).[220] It can not only process single data points (such as images), but also entire sequences of data (such as speech or video).
The technology and methods used to provide imaging-based automatic inspection and analysis for such applications as automatic inspection,
process control, and robot guidance, usually in industry. Machine vision is a term encompassing a large number of technologies, software and hardware products, integrated systems, actions, methods and expertise. Machine vision as a
systems engineering discipline can be considered distinct from
computer vision, a form of
computer science. It attempts to integrate existing technologies in new ways and apply them to solve real world problems. The term is the prevalent one for these functions in industrial automation environments but is also used for these functions in other environments such as security and vehicle guidance.
A
stochastic model describing a
sequence of possible events in which the probability of each event depends only on the state attained in the previous event.[221][222][223]
The capability of a computer system to interpret data in a manner that is similar to the way humans use their senses to relate to the world around them.[227][228][229]
A field in
economics and
game theory that takes an
engineering approach to designing economic mechanisms or
incentives, toward desired objectives, in
strategic settings, where players act
rationally. Because it starts at the end of the game, then goes backwards, it is also called reverse game theory. It has broad applications, from economics and politics (markets, auctions, voting procedures) to networked-systems (internet interdomain routing, sponsored search auctions).
Allows for an in-depth insight into the molecular mechanisms of a particular organism. In particular, these models correlate the
genome with molecular physiology.[232]
In
computer science and
mathematical optimization, a metaheuristic is a higher-level
procedure or
heuristic designed to find, generate, or select a heuristic (partial
search algorithm) that may provide a sufficiently good solution to an
optimization problem, especially with incomplete or imperfect information or limited computation capacity.[233][234] Metaheuristics sample a set of solutions which is too large to be completely sampled.
In
computer science, model checking or property checking is, for a given model of a system, exhaustively and automatically checking whether this model meets a given
specification. Typically, one has hardware or software systems in mind, whereas the specification contains safety requirements such as the absence of
deadlocks and similar critical states that can cause the system to
crash. Model checking is a technique for automatically verifying correctness properties of finite-state systems.
In
propositional logic, modus tollens is a
validargument form and a
rule of inference. It is an application of the general truth that if a statement is true, then so is its
contrapositive. The inference rule modus tollens asserts that the
inference from P implies Q to the negation of Q implies the negation of P is valid.
A variant of
particle swarm optimization (PSO) based on the use of multiple sub-swarms instead of one (standard) swarm. The general approach in multi-swarm optimization is that each sub-swarm focuses on a specific region while a specific diversification method decides where and when to launch the sub-swarms. The multi-swarm framework is especially fitted for the optimization on multi-modal problems, where multiple (local) optima exist.
A
genetic operator used to maintain
genetic diversity from one generation of a population of
genetic algorithmchromosomes to the next. It is analogous to biological
mutation. Mutation alters one or more gene values in a chromosome from its initial state. In mutation, the solution may change entirely from the previous solution. Hence GA can come to a better solution by using mutation. Mutation occurs during evolution according to a user-definable mutation probability. This probability should be set low. If it is set too high, the search will turn into a primitive random search.
An early
backward chainingexpert system that used
artificial intelligence to identify bacteria causing severe infections, such as
bacteremia and
meningitis, and to recommend
antibiotics, with the dosage adjusted for patient's body weight – the name derived from the antibiotics themselves, as many antibiotics have the suffix "-mycin". The MYCIN system was also used for the diagnosis of blood clotting diseases.
An approach used in computer science for
representing basic knowledge about a specific domain, and has been used in applications such as the representation of the meaning of natural language sentences in artificial intelligence applications. In a general setting the term has been used to refer to the use of a limited store of generally understood knowledge about a specific domain in the world, and has been applied to fields such as the knowledge based design of data schemas.[236]
In programming languages, name binding is the association of entities (data and/or code) with
identifiers.[237] An identifier bound to an object is said to
reference that object.
Machine languages have no built-in notion of identifiers, but name-object bindings as a service and notation for the programmer is implemented by programming languages. Binding is intimately connected with
scoping, as scope determines which names bind to which objects – at which locations in the program code (
lexically) and in which one of the possible execution paths (
temporally). Use of an identifier id in a context that establishes a binding for id is called a binding (or defining) occurrence. In all other occurrences (e.g., in expressions, assignments, and subprogram calls), an identifier stands for what it is bound to; such occurrences are called applied occurrences.
Also entity identification, entity chunking, and entity extraction.
A subtask of
information extraction that seeks to locate and classify
named entity mentions in
unstructured text into pre-defined categories such as the person names, organizations, locations,
medical codes, time expressions, quantities, monetary values, percentages, etc.
A key concept of
Semantic Web architecture in which a set of
Resource Description Framework statements (a
graph) are identified using a
URI,[238] allowing descriptions to be made of that set of statements such as context, provenance information or other such
metadata. Named graphs are a simple extension of the RDF data model[239] through which graphs can be created but the model lacks an effective means of distinguishing between them once published on the
Web at large.
A software process that transforms structured data into plain-English content. It can be used to produce long-form content for organizations to automate custom reports, as well as produce custom content for a web or mobile application. It can also be used to generate short blurbs of text in interactive conversations (a
chatbot) which might even be read out loud by a
text-to-speech system.
A subfield of computer science, information engineering, and artificial intelligence concerned with the interactions between computers and human (natural) languages, in particular how to program computers to process and analyze large amounts of
natural language data.
All networks, including biological networks, social networks, technological networks (e.g., computer networks and electrical circuits) and more, can be represented as
graphs, which include a wide variety of subgraphs. One important local property of networks are so-called network motifs, which are defined as recurrent and
statistically significant sub-graphs or patterns.
An approach to
machine translation that uses a large
artificial neural network to predict the likelihood of a sequence of words, typically modeling entire sentences in a single integrated model.
A neural network can refer to either a
neural circuit of biological
neurons (sometimes also called a biological neural network), or a network of
artificial neurons or
nodes in the case of an
artificial neural network.[241] Artificial neural networks are used for solving
artificial intelligence (AI) problems; they model connections of biological neurons as weights between nodes. A positive weight reflects an excitatory connection, while negative values mean inhibitory connections. All inputs are modified by a weight and summed. This activity is referred to as a
linear combination. Finally, an activation function controls the
amplitude of the output. For example, an acceptable range of output is usually between 0 and 1, or it could be −1 and 1.
Also brain–computer interface (BCI), neural-control interface (NCI), mind-machine interface (MMI), direct neural interface (DNI), or brain–machine interface (BMI).
A direct communication pathway between an enhanced or wired
brain and an external device. BCI differs from
neuromodulation in that it allows for bidirectional information flow. BCIs are often directed at researching, mapping, assisting, augmenting, or repairing human cognitive or sensory-motor functions.[244]
A basic unit of a
data structure, such as a
linked list or
tree data structure. Nodes contain
data and also may link to other nodes. Links between nodes are often implemented by
pointers.
Nouvelle AI differs from
classical AI by aiming to produce robots with intelligence levels similar to insects. Researchers believe that intelligence can emerge organically from simple behaviors as these intelligences interacted with the "real world", instead of using the constructed worlds which symbolic AIs typically needed to have programmed into them.[252]
In
computational complexity theory, a problem is NP-complete when it can be solved by a restricted class of
brute force search algorithms and it can be used to simulate any other problem with a similar algorithm. More precisely, each input to the problem should be associated with a set of solutions of polynomial length, whose validity can be tested quickly (in
polynomial time[254]), such that the output for any input is "yes" if the solution set is non-empty and "no" if it is empty.
In
computational complexity theory, the defining property of a class of problems that are, informally, "at least as hard as the hardest problems in NP". A simple example of an NP-hard problem is the
subset sum problem.
The problem-solving principle that states that when presented with competing
hypotheses that make the same predictions, one should select the solution with the fewest assumptions;[255] the principle is not meant to filter out hypotheses that make different predictions. The idea is attributed to the English
Franciscan friar
William of Ockham (
c. 1287–1347), a
scholastic philosopher and
theologian.
A method of
machine learning in which data becomes available in a sequential order and is used to update the best predictor for future data at each step, as opposed to batch learning techniques which generate the best predictor by learning on the entire training data set at once. Online learning is a common technique used in areas of machine learning where it is computationally infeasible to train over the entire dataset, requiring the need of
out-of-core algorithms. It is also used in situations where it is necessary for the algorithm to dynamically adapt to new patterns in the data, or when the data itself is generated as a function of time.
Also ontology extraction, ontology generation, or ontology acquisition.
The automatic or semi-automatic creation of
ontologies, including extracting the corresponding
domain's terms and the relationships between the
concepts that these terms represent from a
corpus of natural language text, and encoding them with an
ontology language for easy retrieval.
The for-profit corporation OpenAI LP, whose
parent organization is the non-profit organization OpenAI Inc[256] that conducts research in the field of
artificial intelligence (AI) with the stated aim to promote and develop
friendly AI in such a way as to benefit humanity as a whole.
A generalization of a
Markov decision process (MDP). A POMDP models an agent decision process in which it is assumed that the system dynamics are determined by an MDP, but the agent cannot directly observe the underlying state. Instead, it must maintain a probability distribution over the set of possible states, based on a set of observations and observation probabilities, and the underlying MDP.
A computational method that
optimizes a problem by
iteratively trying to improve a
candidate solution with regard to a given measure of quality. It solves a problem by having a population of candidate solutions, here dubbed
particles, and moving these particles around in the
search-space according to simple
mathematical formulae over the particle's position and velocity. Each particle's movement is influenced by its local best known position, but is also guided toward the best known positions in the search-space, which are updated as better positions are found by other particles. This is expected to move the swarm toward the best solutions.
The plotting, by a computer application, of the shortest route between two points. It is a more practical variant on
solving mazes. This field of research is based heavily on
Dijkstra's algorithm for finding a shortest path on a
weighted graph.
Concerned with the automatic discovery of regularities in data through the use of computer algorithms and with the use of these regularities to take actions such as classifying the data into different categories.[260]
Also first-order logic, predicate logic, and first-order predicate calculus.
A collection of
formal systems used in
mathematics,
philosophy,
linguistics, and
computer science. First-order logic uses
quantified variables over non-logical objects and allows the use of sentences that contain variables, so that rather than propositions such as Socrates is a man one can have expressions in the form "there exists x such that x is Socrates and x is a man" and there exists is a quantifier while x is a variable.[179] This distinguishes it from
propositional logic, which does not use quantifiers or
relations;[261] in this sense, propositional logic is the foundation of first-order logic.
A statistical procedure that uses an
orthogonal transformation to convert a set of observations of possibly correlated variables (entities each of which takes on various numerical values) into a set of values of
linearly uncorrelated variables called principal components. This transformation is defined in such a way that the first principal component has the largest possible
variance (that is, accounts for as much of the variability in the data as possible), and each succeeding component, in turn, has the highest variance possible under the constraint that it is
orthogonal to the preceding components. The resulting vectors (each being a
linear combination of the variables and containing n observations) are an uncorrelated
orthogonal basis set. PCA is sensitive to the relative scaling of the original variables.
A principle coined by
Karl R. Popper in his Harvard Lecture of 1963, and published in his book Myth of Framework.[264] It is related to what he called the 'logic of the situation' in an Economica article of 1944/1945, published later in his book The Poverty of Historicism.[265] According to Popper's rationality principle, agents act in the most adequate way according to the objective situation. It is an idealized conception of human behavior which he used to drive his model of
situational analysis.
A
programming paradigm in which
probabilistic models are specified and inference for these models is performed automatically.[266] It represents an attempt to unify probabilistic modeling and traditional general-purpose programming in order to make the former easier and more widely applicable.[267][268] It can be used to create systems that help make decisions in the face of uncertainty. Programming languages used for probabilistic programming are referred to as "Probabilistic programming languages" (PPLs).
Also propositional logic, statement logic, sentential calculus, sentential logic, and zeroth-order logic.
A branch of
logic which deals with
propositions (which can be true or false) and argument flow. Compound propositions are formed by connecting propositions by
logical connectives. The propositions without logical connectives are called atomic propositions. Unlike
first-order logic, propositional logic does not deal with non-logical objects, predicates about them, or quantifiers. However, all the machinery of propositional logic is included in first-order logic and higher-order logics. In this sense, propositional logic is the foundation of first-order logic and higher-order logic.
In philosophy and artificial intelligence (especially
knowledge-based systems), the qualification problem is concerned with the impossibility of listing all of the
preconditions required for a real-world action to have its intended effect.[274][275] It might be posed as how to deal with the things that prevent me from achieving my intended result. It is strongly connected to, and opposite the
ramification side of, the
frame problem.[274]
In
logic, quantification specifies the quantity of specimens in the
domain of discourse that satisfy an
open formula. The two most common quantifiers mean "
for all" and "
there exists". For example, in arithmetic, quantifiers allow one to say that the natural numbers go on forever, by writing that for all n (where n is a natural number), there is another number (say, the successor of n) which is one bigger than n.
Query languages or data query languages (DQLs) are
computer languages used to make queries in
databases and
information systems. Broadly, query languages can be classified according to whether they are database query languages or
information retrieval query languages. The difference is that a database query language attempts to give factual answers to factual questions, while an information retrieval query language attempts to find documents containing information that is relevant to an area of inquiry.
An
ensemble learning method for
classification,
regression and other tasks that operates by constructing a multitude of
decision trees at training time and outputting the class that is the
mode of the classes (classification) or mean prediction (regression) of the individual trees.[283][284] Random decision forests correct for decision trees' habit of
overfitting to their
training set.[285]
An area of
machine learning concerned with how
software agents ought to take
actions in an environment so as to maximize some notion of cumulative reward. Reinforcement learning is one of three basic machine learning paradigms, alongside
supervised learning and
unsupervised learning. It differs from supervised learning in that labelled input/output pairs need not be presented, and sub-optimal actions need not be explicitly corrected. Instead the focus is finding a balance between exploration (of uncharted territory) and exploitation (of current knowledge).[289]
A technique that involve training a "reward model" to predict how humans rate the quality of generated content, and then training a
generative AI model to satisfy this reward model via
reinforcement learning. It can be used for example to make the generative AI model more truthful or less harmful.[290]
A framework for computation that may be viewed as an extension of
neural networks.[291] Typically an input signal is fed into a fixed (random)
dynamical system called a reservoir and the dynamics of the reservoir map the input to a higher dimension. Then a simple readout mechanism is trained to read the state of the reservoir and map it to the desired output. The main benefit is that training is performed only at the readout stage and the reservoir is fixed.
Liquid-state machines[292] and
echo state networks[293] are two major types of reservoir computing.[294]
A
pattern matchingalgorithm for implementing
rule-based systems. The algorithm was developed to efficiently apply many
rules or patterns to many objects, or
facts, in a
knowledge base. It is used to determine which of the system's rules should fire based on its data store, its facts.
In
computer science, a rule-based system is used to store and manipulate knowledge to interpret information in a useful way. It is often used in artificial intelligence applications and research. Normally, the term rule-based system is applied to systems involving human-crafted or curated rule sets. Rule-based systems constructed using automatic rule inference, such as
rule-based machine learning, are normally excluded from this system type.
In
mathematical logic, satisfiability and
validity are elementary concepts of
semantics. A
formula is satisfiable if it is possible to find an
interpretation (
model) that makes the formula true.[296] A formula is valid if all interpretations make the formula true. The opposites of these concepts are unsatisfiability and invalidity, that is, a formula is unsatisfiable if none of the interpretations make the formula true, and invalid if some such interpretation makes the formula false. These four concepts are related to each other in a manner exactly analogous to
Aristotle's
square of opposition.
Allows for queries and analytics of associative and
contextual nature. Semantic queries enable the retrieval of both explicitly and implicitly derived information based on syntactic, semantic and structural information contained in data. They are designed to deliver precise results (possibly the distinctive selection of one single piece of information) or to answer more fuzzy and wide-open questions through
pattern matching and
digital reasoning.
In
programming language theory, semantics is the field concerned with the rigorous mathematical study of the meaning of
programming languages. It does so by evaluating the meaning of
syntactically valid
strings defined by a specific programming language, showing the computation involved. In such a case that the evaluation would be of syntactically invalid strings, the result would be non-computation. Semantics describes the processes a computer follows when executing a program in that specific language. This can be shown by describing the relationship between the input and output of a program, or an explanation of how the program will be executed on a certain
platform, hence creating a
model of computation.
The combining of
sensory data or data derived from disparate sources such that the resulting
information has less uncertainty than would be possible when these sources were used individually.
An area of supervised
machine learning in artificial intelligence. It is closely related to
regression and
classification, but the goal is to learn from a similarity function that measures how similar or related two objects are. It has applications in
ranking, in
recommendation systems, visual identity tracking, face verification, and speaker verification.
In artificial intelligence research, the situated approach builds agents that are designed to behave effectively successfully in their environment. This requires designing AI "from the bottom-up" by focussing on the basic perceptual and motor skills required to survive. The situated approach gives a much lower priority to abstract reasoning or problem-solving skills.
An area of artificial intelligence which draws from the fields of
computer science,
cognitive science, and
cognitive psychology. The theoretic goal—on the cognitive side—involves representing and reasoning spatial-temporal knowledge in mind. The applied goal—on the computing side—involves developing high-level control systems of automata for
navigating and understanding time and space.
An interdisciplinary subfield of
computational linguistics that develops methodologies and technologies that enables the recognition and
translation of spoken language into text by computers. It is also known as automatic speech recognition (ASR), computer speech recognition or speech to text (STT). It incorporates knowledge and research in the
linguistics,
computer science, and
electrical engineering fields.
In
information technology and
computer science, a program is described as stateful if it is designed to remember preceding events or user interactions;[305] the remembered information is called the state of the system.
In
machine learning and
statistics, classification is the problem of identifying to which of a set of
categories (sub-populations) a new observation belongs, on the basis of a
training set of data containing observations (or instances) whose category membership is known. Examples are assigning a given email to the
"spam" or "non-spam" class, and assigning a diagnosis to a given patient based on observed characteristics of the patient (sex, blood pressure, presence or absence of certain symptoms, etc.). Classification is an example of
pattern recognition.
Any
optimizationmethod that generates and uses
random variables. For stochastic problems, the random variables appear in the formulation of the optimization problem itself, which involves random
objective functions or random constraints. Stochastic optimization methods also include methods with random iterates. Some stochastic optimization methods use random iterates to solve stochastic problems, combining both meanings of stochastic optimization.[308] Stochastic optimization methods generalize
deterministic methods for deterministic problems.
An approach used in
computer science as a
semantic component of
natural language understanding. Stochastic models generally use the definition of segments of words as basic semantic units for the semantic models, and in some cases involve a two layered approach.[309]
A hypothetical
agent that possesses
intelligence far surpassing that of the
brightest and most
gifted human minds. Superintelligence may also refer to a property of problem-solving systems (e.g., superintelligent language translators or engineering assistants) whether or not these high-level intellectual competencies are embodied in agents that act within the physical world. A superintelligence may or may not be created by an
intelligence explosion and be associated with a
technological singularity.
The
machine learning task of learning a function that maps an input to an output based on example input-output pairs.[310] It infers a function from labeled
training data consisting of a set of training examples.[311] In supervised learning, each example is a pair consisting of an input object (typically a vector) and a desired output value (also called the supervisory signal). A supervised learning algorithm analyzes the training data and produces an inferred function, which can be used for mapping new examples. An optimal scenario will allow for the algorithm to correctly determine the class labels for unseen instances. This requires the learning algorithm to generalize from the training data to unseen situations in a "reasonable" way (see
inductive bias).
The term for the collection of all methods in
artificial intelligence research that are based on high-level "symbolic" (human-readable) representations of problems,
logic, and
search.
An alternative term for
artificial intelligence which emphasizes that the intelligence of machines need not be an imitation or in any way artificial; it can be a genuine form of intelligence.[314][315]
A
hypothetical point in the future when technological growth becomes uncontrollable and irreversible, resulting in unfathomable changes to human civilization.[316][317][318]
A
heuristic for choosing actions that addresses the exploration-exploitation dilemma in the
multi-armed bandit problem. It consists in choosing the action that maximizes the expected reward with respect to a randomly drawn belief.[324][325]
The
computational complexity that describes the amount of time it takes to run an
algorithm. Time complexity is commonly estimated by counting the number of elementary operations performed by the algorithm, supposing that each elementary operation takes a fixed amount of time to perform. Thus, the amount of time taken and the number of elementary operations performed by the algorithm are taken to differ by at most a
constant factor.
In
theoretical computer science, a transition system is a concept used in the study of
computation. It is used to describe the potential behavior of
discrete systems. It consists of
states and transitions between states, which may be labeled with labels chosen from a set; the same label may appear on more than one transition. If the label set is a
singleton, the system is essentially unlabeled, and a simpler definition that omits the labels is possible.
A form of
graph traversal and refers to the process of visiting (checking and/or updating) each node in a
tree data structure, exactly once. Such traversals are classified by the order in which the nodes are visited.
In
computational complexity theory, the language TQBF is a
formal language consisting of the true quantified Boolean formulas. A (fully) quantified Boolean formula is a formula in
quantifiedpropositional logic where every variable is quantified (or
bound), using either
existential or
universal quantifiers, at the beginning of the sentence. Such a formula is equivalent to either true or false (since there are no
free variables). If such a formula evaluates to true, then that formula is in the language TQBF. It is also known as QSAT (Quantified
SAT).
A test of a machine's ability to exhibit intelligent behaviour equivalent to, or indistinguishable from, that of a human, developed by
Alan Turing in 1950. Turing proposed that a human evaluator would
judge natural language conversations between a human and a machine designed to generate human-like responses. The evaluator would be aware that one of the two partners in conversation is a machine, and all participants would be separated from one another. The conversation would be limited to a text-only channel such as a
computer keyboard and
screen so the result would not depend on the machine's ability to render words as speech.[329] If the evaluator cannot reliably tell the machine from the human, the machine is said to have passed the test. The test results do not depend on the machine's ability to give correct answers to questions, only how closely its answers resemble those a human would give.
In
programming languages, a set of rules that assigns a property called
type to the various constructs of a
computer program, such as
variables,
expressions,
functions, or
modules.[330] These types formalize and enforce the otherwise implicit categories the programmer uses for
algebraic data types, data structures, or other components (e.g. "string", "array of float", "function returning boolean"). The main purpose of a type system is to reduce possibilities for
bugs in computer programs[331] by defining
interfaces between different parts of a computer program, and then checking that the parts have been connected in a consistent way. This checking can happen statically (at
compile time), dynamically (at
run time), or as a combination of static and dynamic checking. Type systems have other purposes as well, such as expressing business rules, enabling certain compiler optimizations, allowing for
multiple dispatch, providing a form of documentation, etc.
A type of self-organized
Hebbian learning that helps find previously unknown patterns in data set without pre-existing labels. It is also known as
self-organization and allows modeling
probability densities of given inputs.[332] It is one of the main three categories of machine learning, along with
supervised and
reinforcement learning. Semi-supervised learning has also been described and is a hybridization of supervised and unsupervised techniques.
^
abFor example: Josephson, John R.; Josephson, Susan G., eds. (1994). Abductive Inference: Computation, Philosophy, Technology. Cambridge, UK; New York: Cambridge University Press.
doi:
10.1017/CBO9780511530128.
ISBN978-0521434614.
OCLC28149683.
^"Retroduction". Commens – Digital Companion to C. S. Peirce. Mats Bergman, Sami Paavola & João Queiroz. Archived from
the original on 5 July 2022. Retrieved 24 August 2014.
^Abraham, A. (2005), "Adaptation of Fuzzy Inference System Using Neural Learning", in Nedjah, Nadia; De Macedo Mourelle, Luiza (eds.), Fuzzy Systems Engineering: Theory and Practice, Studies in Fuzziness and Soft Computing, vol. 181, Germany: Springer Verlag, pp. 53–83,
CiteSeerX10.1.1.161.6135,
doi:
10.1007/11339366_3,
ISBN978-3-540-25322-8
^Tao, Jianhua; Tieniu Tan (2005). "Affective Computing: A Review". Affective Computing and Intelligent Interaction. Vol.
LNCS 3784. Springer. pp. 981–995.
doi:
10.1007/11573548.
^El Kaliouby, Rana (November–December 2017).
"We Need Computers with Empathy". Technology Review. Vol. 120, no. 6. p. 8. Archived from
the original on 7 July 2018. Retrieved 6 November 2018.
^Shapiro, Stuart C. (1992).
Artificial Intelligence In Stuart C. Shapiro (Ed.), Encyclopedia of Artificial Intelligence (Second Edition, pp. 54–57). New York: John Wiley. (Section 4 is on "AI-Complete Tasks".)
Poole, Mackworth & Goebel 1998,
p. 1, which provides the version that is used in this article. Note that they use the term "computational intelligence" as a synonym for artificial intelligence.
^Gehrig, Stefan K.; Stein, Fridtjof J. (1999). Dead reckoning and cartography using stereo vision for an automated car. IEEE/RSJ International Conference on Intelligent Robots and Systems. Vol. 3. Kyongju. pp. 1507–1512.
doi:
10.1109/IROS.1999.811692.
ISBN0-7803-5184-3.
^Ioffe, Sergey; Szegedy, Christian (2015). "Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift".
arXiv:1502.03167 [
cs.LG].
^Pham DT, Ghanbarzadeh A, Koc E, Otri S, Rahim S and Zaidi M. The Bees Algorithm. Technical Note, Manufacturing Engineering Centre, Cardiff University, UK, 2005.
^Erman, L. D.; Hayes-Roth, F.; Lesser, V. R.; Reddy, D. R. (1980). "The Hearsay-II Speech-Understanding System: Integrating Knowledge to Resolve Uncertainty". ACM Computing Surveys. 12 (2): 213.
doi:
10.1145/356810.356816.
S2CID118556.
^Corkill, Daniel D. (September 1991).
"Blackboard Systems"(PDF). AI Expert. 6 (9): 40–47. Archived from
the original(PDF) on 16 April 2012. Retrieved 5 July 2022.
^* Nii, H. Yenny (1986).
Blackboard Systems(PDF) (Technical report). Department of Computer Science, Stanford University. STAN-CS-86-1123. Retrieved 12 April 2013.
^Fisher, Douglas H. (July 1987). "Improving inference through conceptual clustering". Proceedings of the 1987 AAAI Conferences. AAAI Conference. Seattle Washington. pp. 461–465.
^Iba, William; Langley, Pat (27 January 2011). "Cobweb models of categorization and probabilistic concept formation". In Pothos, Emmanuel M.; Wills, Andy J. (eds.). Formal approaches in categorization. Cambridge: Cambridge University Press. pp. 253–273.
ISBN9780521190480.
^Cognitive science is an interdisciplinary field of researchers from Linguistics, psychology, neuroscience, philosophy, computer science, and anthropology that seek to understand the mind.
How We Learn: Ask the Cognitive Scientist
^Schrijver, Alexander (February 1, 2006). A Course in Combinatorial Optimization (PDF), page 1.
^HAYKIN, S. Neural Networks - A Comprehensive Foundation. Second edition. Pearson Prentice Hall: 1999.
^Hulstijn, J, and Nijholt, A. (eds.). Proceedings of the International Workshop on Computational Humor. Number 12 in Twente Workshops on Language Technology, Enschede, Netherlands. University of Twente, 1996.
^Trappenberg, Thomas P. (2002). Fundamentals of Computational Neuroscience. United States: Oxford University Press Inc. p. 1.
ISBN978-0-19-851582-1.
^What is computational neuroscience? Patricia S. Churchland, Christof Koch, Terrence J. Sejnowski. in Computational Neuroscience pp.46-55. Edited by Eric L. Schwartz. 1993. MIT Press
"Computational Neuroscience Edited by Eric L. Schwartz". Archived from
the original on 4 June 2011. Retrieved 11 June 2009.
^Kramer, GJE; Grierson, DE (1989). "Computer automated design of structures under dynamic loads". Computers & Structures. 32 (2): 313–325.
doi:
10.1016/0045-7949(89)90043-6.
^Moharrami, H; Grierson, DE (1993). "Computer-Automated Design of Reinforced Concrete Frameworks". Journal of Structural Engineering. 119 (7): 2036–2058.
doi:
10.1061/(asce)0733-9445(1993)119:7(2036).
^Xu, L; Grierson, DE (1993). "Computer-Automated Design of Semirigid Steel Frameworks". Journal of Structural Engineering. 119 (6): 1740–1760.
doi:
10.1061/(asce)0733-9445(1993)119:6(1740).
^Barsan, GM; Dinsoreanu, M, (1997). Computer-automated design based on structural performance criteria, Mouchel Centenary Conference on Innovation in Civil and Structural Engineering, Aug 19-21, Cambridge England, Innovation in Civil and Structural Engineering, 167-172
^Li, Yun (1996). "Genetic algorithm automated approach to the design of sliding mode control systems". International Journal of Control. 63 (4): 721–739.
doi:
10.1080/00207179608921865.
^Barsan, GM, (1995) Computer-automated design of semirigid steel frameworks according to EUROCODE-3, Nordic Steel Construction Conference 95, JUN 19-21, 787-794
^Dana H. Ballard; Christopher M. Brown (1982). Computer Vision. Prentice Hall.
ISBN0-13-165316-4.
^Huang, T. (1996-11-19). Vandoni, Carlo, E, ed. Computer Vision : Evolution And Promise (PDF). 19th CERN School of Computing. Geneva: CERN. pp. 21–25.
doi:
10.5170/CERN-1996-008.21.
ISBN978-9290830955.
^Milan Sonka; Vaclav Hlavac; Roger Boyle (2008). Image Processing, Analysis, and Machine Vision. Thomson.
ISBN0-495-08252-X.
^Garson, James (27 November 2018). Zalta, Edward N. (ed.).
The Stanford Encyclopedia of Philosophy. Metaphysics Research Lab, Stanford University – via Stanford Encyclopedia of Philosophy.
^Zhang, Wei (1988). "Shift-invariant pattern recognition neural network and its optical architecture". Proceedings of annual conference of the Japan Society of Applied Physics.
^Solomonoff, R.J.The Time Scale of Artificial Intelligence; Reflections on Social Effects, Human Systems Management, Vol 5 1985, Pp 149-153
^Moor, J., The Dartmouth College Artificial Intelligence Conference: The Next Fifty years, AI Magazine, Vol 27, No., 4, Pp. 87-9, 2006
^Kline, Ronald R., Cybernetics, Automata Studies and the Dartmouth Conference on Artificial Intelligence, IEEE Annals of the History of Computing, October–December, 2011, IEEE Computer Society
^Huang; Green; Loo, "Datalog and Emerging applications",
SIGMOD 2011(PDF), UC Davis, archived from
the original(PDF) on 1 July 2022, retrieved 5 July 2022.
^Steele, Katie and Stefánsson, H. Orri, "Decision Theory", The Stanford Encyclopedia of Philosophy (Winter 2015 Edition), Edward N. Zalta (ed.), URL =
[1]
^Lloyd, J.W., Practical Advantages of Declarative Programming
^
abBengio, Y.; Courville, A.; Vincent, P. (2013). "Representation Learning: A Review and New Perspectives". IEEE Transactions on Pattern Analysis and Machine Intelligence. 35 (8): 1798–1828.
arXiv:1206.5538.
doi:
10.1109/tpami.2013.50.
PMID23787338.
S2CID393948.
^Chang, Ziyi; Koulieris, George Alex; Shum, Hubert P. H. (2023). "On the Design Fundamentals of Diffusion Models: A Survey".
arXiv:2306.04542 [
cs.LG].
^Croitoru, Florinel-Alin; Hondru, Vlad; Ionescu, Radu Tudor; Shah, Mubarak (2023). "Diffusion Models in Vision: A Survey". IEEE Transactions on Pattern Analysis and Machine Intelligence. 45 (9): 10850–10869.
arXiv:2209.04747.
doi:
10.1109/TPAMI.2023.3261988.
PMID37030794.
S2CID252199918.
^
abOstrow, Adam (5 March 2011).
"Roger Ebert's Inspiring Digital Transformation". Mashable Entertainment. Retrieved 12 September 2011. With the help of his wife, two colleagues and the Alex-equipped MacBook that he uses to generate his computerized voice, famed film critic Roger Ebert delivered the final talk at the TED conference on Friday in Long Beach, California....
^Lee, Jennifer (7 March 2011).
"Roger Ebert Tests His Vocal Cords, and Comedic Delivery". The New York Times. Retrieved 12 September 2011. Now perhaps, there is the Ebert Test, a way to see if a synthesized voice can deliver humor with the timing to make an audience laugh.... He proposed the Ebert Test as a way to gauge the humanness of a synthesized voice.
^"Roger Ebert's Inspiring Digital Transformation". Tech News. 5 March 2011. Archived from
the original on 25 March 2011. Retrieved 12 September 2011. Meanwhile, the technology that enables Ebert to "speak" continues to see improvements – for example, adding more realistic inflection for question marks and exclamation points. In a test of that, which Ebert called the "Ebert test" for computerized voices,
^Vikhar, P. A. (2016). "Evolutionary algorithms: A critical review and its future prospects". 2016 International Conference on Global Trends in Signal Processing, Information Computing and Communication (ICGTSPICC). Jalgaon, 2016, pp. 261-265. pp. 261–265.
doi:
10.1109/ICGTSPICC.2016.7955308.
ISBN978-1-5090-0467-6.
S2CID22100336.
^Myerson, Roger B. (1991). Game Theory: Analysis of Conflict, Harvard University Press, p.
1. Chapter-preview links, pp.
vii–xi.
^Pell, Barney (1992). H. van den Herik; L. Allis (eds.).
"Metagame: a new challenge for games and learning" [Heuristic programming in artificial intelligence 3–the third computerolympiad] (PDF). Ellis-Horwood. Archived from
the original(PDF) on 17 February 2020. Retrieved 13 June 2020.
^Genesereth, Michael; Love, Nathaniel; Pell, Barney (15 June 2005). "General Game Playing: Overview of the AAAI Competition". AI Magazine. 26 (2): 62.
doi:
10.1609/aimag.v26i2.1813.
ISSN2371-9621.
^Andrej Karpathy; Pieter Abbeel; Greg Brockman; Peter Chen; Vicki Cheung; Yan Duan; Ian Goodfellow; Durk Kingma; Jonathan Ho; Rein Houthooft; Tim Salimans; John Schulman; Ilya Sutskever; Wojciech Zaremba (16 June 2016).
"Generative models". OpenAI.
^Trudeau, Richard J. (1993).
Introduction to Graph Theory (Corrected, enlarged republication. ed.). New York: Dover Pub. p. 19.
ISBN978-0-486-67870-2. Retrieved 8 August 2012. A graph is an object consisting of two sets called its vertex set and its edge set.
^E. K. Burke, E. Hart,
G. Kendall, J. Newall, P. Ross, and S. Schulenburg, Hyper-heuristics: An emerging direction in modern search technology, Handbook of Metaheuristics (F. Glover and G. Kochenberger, eds.), Kluwer, 2003, pp. 457–474.
^P. Ross, Hyper-heuristics, Search Methodologies: Introductory Tutorials in Optimization and Decision Support Techniques (E. K. Burke and
G. Kendall, eds.), Springer, 2005, pp. 529-556.
^Ozcan, E.; Bilgin, B.; Korkmaz, E. E. (2008). "A Comprehensive Analysis of Hyper-heuristics". Intelligent Data Analysis. 12 (1): 3–23.
doi:
10.3233/ida-2008-12102.
^Oudeyer, Pierre-Yves; Kaplan, Frederic (2008). "How can we define intrinsic motivation?". Proc. of the 8th Conf. on Epigenetic Robotics. Vol. 5. pp. 29–31.
^Schank, Roger; Robert Abelson (1977). Scripts, Plans, Goals, and Understanding: An Inquiry Into Human Knowledge Structures. Lawrence Erlbaum Associates, Inc.
^Siegelmann, Hava T.; Sontag, Eduardo D. (1992). "On the computational power of neural nets". Proceedings of the fifth annual workshop on Computational learning theory. Vol. COLT '92. pp. 440–449.
doi:
10.1145/130385.130432.
ISBN978-0897914970.
S2CID207165680. {{
cite book}}: |work= ignored (
help)
^Gagniuc, Paul A. (2017). Markov Chains: From Theory to Implementation and Experimentation. USA, NJ: John Wiley & Sons. pp. 1–235.
ISBN978-1-119-38755-8.
^Franke; Siezen, Teusink (2005). "Reconstructing the metabolic network of a bacterium from its genome". Trends in Microbiology. 13 (11): 550–558.
doi:
10.1016/j.tim.2005.09.001.
PMID16169729.
^Herbert B. Enderton, 2001, A Mathematical Introduction to Logic Second Edition Enderton:110, Harcourt Academic Press, Burlington MA,
ISBN978-0-12-238452-3.
^Bishop, Christopher M. (2006). Pattern Recognition and Machine Learning (PDF). Springer. p. vii. Pattern recognition has its origins in engineering, whereas machine learning grew out of computer science. However, these activities can be viewed as two facets of the same field, and together they have undergone substantial development over the past ten years.
^Nyce, Charles (2007),
Predictive Analytics White Paper(PDF), American Institute for Chartered Property Casualty Underwriters/Insurance Institute of America, p. 1
^Clocksin, William F.; Mellish, Christopher S. (2003). Programming in Prolog. Berlin; New York: Springer-Verlag.
ISBN978-3-540-00678-7.
^Bratko, Ivan (2012). Prolog programming for artificial intelligence (4th ed.). Harlow, England; New York: Addison Wesley.
ISBN978-0-321-41746-6.
^Covington, Michael A. (1994). Natural language processing for Prolog programmers. Englewood Cliffs, N.J.: Prentice Hall.
ISBN978-0-13-629213-5.
^Lloyd, J. W. (1984). Foundations of logic programming. Berlin: Springer-Verlag.
ISBN978-3-540-13299-8.
^Kuhlman, Dave. "A Python Book: Beginning Python, Advanced Python, and Python Exercises". Section 1.1. Archived from the original (PDF) on 23 June 2012.
^Thielscher, Michael (September 2001). "The Qualification Problem: A solution to the problem of anomalous models". Artificial Intelligence. 131 (1–2): 1–37.
doi:
10.1016/S0004-3702(01)00131-X.
^ R language and environment
Hornik, Kurt (4 October 2017).
"R FAQ". The Comprehensive R Archive Network. 2.1 What is R?. Retrieved 6 August 2018.
R Foundation
Hornik, Kurt (4 October 2017).
"R FAQ". The Comprehensive R Archive Network. 2.13 What is the R Foundation?. Retrieved 6 August 2018.
The R Core Team asks authors who use R in their data analysis to cite the software using:
R Core Team (2016). R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. URL
https://R-project.org/.
^Vance, Ashlee (6 January 2009).
"Data Analysts Captivated by R's Power". The New York Times. Retrieved 6 August 2018. R is also the name of a popular programming language used by a growing number of data analysts inside corporations and academia. It is becoming their lingua franca...
^Ho, Tin Kam (1995). Random Decision Forests (PDF). Proceedings of the 3rd International Conference on Document Analysis and Recognition, Montreal, QC, 14–16 August 1995. pp. 278–282. Archived from the original (PDF) on 17 April 2016. Retrieved 5 June 2016.
^Li, Xiangang; Wu, Xihong (15 October 2014). "Constructing Long Short-Term Memory based Deep Recurrent Neural Networks for Large Vocabulary Speech Recognition".
arXiv:1410.4281 [
cs.CL].
^Schrauwen, Benjamin,
David Verstraeten, and
Jan Van Campenhout. "An overview of reservoir computing: theory, applications, and implementations." Proceedings of the European Symposium on Artificial Neural Networks ESANN 2007, pp. 471-482.
^Jaeger, Herbert, "The echo state approach to analyzing and training recurrent neural networks." Technical Report 154 (2001), German National Research Center for Information Technology.
^Maass, Wolfgang (1997). "Networks of spiking neurons: The third generation of neural network models". Neural Networks. 10 (9): 1659–1671.
doi:
10.1016/S0893-6080(97)00011-7.
ISSN0893-6080.
^Beni, G.; Wang, J. (1993). "Swarm Intelligence in Cellular Robotic Systems". Proceed. NATO Advanced Workshop on Robots and Biological Systems, Tuscany, Italy, June 26–30 (1989). pp. 703–712.
doi:
10.1007/978-3-642-58069-7_38.
ISBN978-3-642-63461-1.
^Pellionisz, A.; Llinás, R. (1985). "Tensor Network Theory Of The Metaorganization Of Functional Geometries In The Central Nervous System". Neuroscience. 16 (2): 245–273.
doi:
10.1016/0306-4522(85)90001-6.
PMID4080158.
S2CID10747593.
^"TensorFlow: Open source machine learning" "It is machine learning software being used for various kinds of perceptual and language understanding tasks" — Jeffrey Dean, minute 0:47 / 2:17 from YouTube clip
^Sipser, Michael (2013). Introduction to the Theory of Computation 3rd. Cengage Learning.
ISBN978-1-133-18779-0. central areas of the theory of computation: automata, computability, and complexity. (Page 1)
^Thompson, William R (1933). "On the likelihood that one unknown probability exceeds another in view of the evidence of two samples". Biometrika. 25 (3–4): 285–294.
doi:
10.1093/biomet/25.3-4.285.
^Russo, Daniel J.; Van Roy, Benjamin; Kazerouni, Abbas; Osband, Ian; Wen, Zheng (2018). "A Tutorial on Thompson Sampling". Foundations and Trends in Machine Learning. 11 (1): 1–96.
arXiv:1707.02038.
doi:
10.1561/2200000070.
S2CID3929917.
^Turing originally suggested a
teleprinter, one of the few text-only communication systems available in 1950. (
Turing 1950, p. 433)
^Pierce 2002, p. 1: "A type system is a tractable syntactic method for proving the absence of certain program behaviors by classifying phrases according to the kinds of values they compute."
^Cardelli 2004, p. 1: "The fundamental purpose of a type system is to prevent the occurrence of execution errors during the running of a program."
^Hinton, Jeffrey; Sejnowski, Terrence (1999). Unsupervised Learning: Foundations of Neural Computation. MIT Press.
ISBN978-0262581684.
Abran, Alain; Moore, James W.; Bourque, Pierre; Dupuis, Robert; Tripp, Leonard L. (2004). Guide to the Software Engineering Body of Knowledge. IEEE.
ISBN978-0-7695-2330-9.
^polynomial time refers to how quickly the number of operations needed by an algorithm, relative to the size of the problem, grows. It is therefore a measure of efficiency of an algorithm.