Content deleted Content added
grammar Tags: Visual edit Mobile edit Mobile web edit |
→Neuro-symbolic AI: integrating neural and symbolic approaches: added link to main article Neuro-symbolic AI |
||
| (40 intermediate revisions by 23 users not shown) | |||
Line 1:
{{Short description|Methods in artificial intelligence research}}
{{Artificial intelligence|Approaches}}
In [[artificial intelligence]], '''symbolic artificial intelligence''' (also known as '''classical artificial intelligence ''' or '''logic-based artificial intelligence''')<ref>{{cite journal |last1=Garnelo |first1=Marta |last2=Shanahan |first2=Murray |title=Reconciling deep learning with symbolic artificial intelligence: representing objects and relations |journal=Current Opinion in Behavioral Sciences |date=October 2019 |volume=29 |pages=17–23 |doi=10.1016/j.cobeha.2018.12.010|doi-access=free |hdl=10044/1/67796 |hdl-access=free }}</ref><ref>{{Cite SEP|url-id=thomason|title=Logic-Based Artificial Intelligence|first=Richmond|last=Thomason|date=February 27, 2024}}</ref>
Symbolic AI was the dominant [[paradigm]] of AI research from the mid-1950s until the mid-1990s.{{sfn|Kolata|1982}} Researchers in the 1960s and the 1970s were convinced that symbolic approaches would eventually succeed in creating a machine with [[artificial general intelligence]] and considered this the ultimate goal of their field.<ref>{{
[[Artificial neural network|Neural networks]], a subsymbolic approach, had been pursued from early days and reemerged strongly in 2012. Early examples are [[Frank Rosenblatt|Rosenblatt]]'s [[perceptron]] learning work, the [[backpropagation]] work of Rumelhart, Hinton and Williams,<ref>{{cite journal| doi = 10.1038/323533a0| issn = 1476-4687| volume = 323| issue = 6088| pages = 533–536| last1 = Rumelhart| first1 = David E.| last2 = Hinton| first2 = Geoffrey E.| last3 = Williams| first3 = Ronald J.| title = Learning representations by back-propagating errors| journal = Nature| date = 1986 | bibcode = 1986Natur.323..533R| s2cid = 205001834}}</ref> and work in [[convolutional neural network]]s by LeCun et al. in 1989.<ref>{{Cite journal| volume = 1| issue = 4| pages = 541–551| last1 = LeCun| first1 = Y.| last2 = Boser| first2 = B.| last3 = Denker| first3 = I.| last4 = Henderson| first4 = D.| last5 = Howard| first5 = R.| last6 = Hubbard| first6 = W.| last7 = Tackel| first7 = L.| title = Backpropagation Applied to Handwritten Zip Code Recognition| journal = Neural Computation| date = 1989| doi = 10.1162/neco.1989.1.4.541| s2cid = 41312633}}</ref> However, neural networks were not viewed as successful until about 2012: "Until Big Data became commonplace, the general consensus in the Al community was that the so-called neural-network approach was hopeless. Systems just didn't work that well, compared to other methods. ... A revolution came in 2012, when a number of people, including a team of researchers working with Hinton, worked out a way to use the power of [[GPUs]] to enormously increase the power of neural networks."{{sfn|Marcus |Davis|2019}} Over the next several years, [[deep learning]] had spectacular success in handling vision, [[speech recognition]], speech synthesis, image generation, and machine translation. However, since 2020, as inherent difficulties with bias, explanation, comprehensibility, and robustness became more apparent with deep learning approaches; an increasing number of AI researchers have called for [[Neuro-symbolic AI|combining]] the best of both the symbolic and neural network approaches<ref name="Rossi">
{{cite web |last1=Rossi |first1=Francesca |title=Thinking Fast and Slow in AI |url=https://aaai-2022.virtualchair.net/plenary_13.html |publisher=AAAI |access-date=5 July 2022}}</ref><ref name="Selman">
{{cite web |last1=Selman |first1=Bart |title=AAAI Presidential Address: The State of AI |url=https://aaai-2022.virtualchair.net/plenary_2.html |publisher=AAAI |access-date=5 July 2022}}</ref> and addressing areas that both approaches have difficulty with, such as [[Commonsense reasoning|common-sense reasoning]].{{sfn|Marcus |Davis|2019}}
Line 69:
[[Edward Feigenbaum]] said:
* "In the knowledge lies the power."<ref name="Feigenbaum">{{Cite journal| doi = 10.1145/1743546.1743564| issn = 0001-0782| volume = 53| issue = 6| pages = 41–45| last = Shustek| first = Len| title = An interview with Ed Feigenbaum| journal = Communications of the ACM| accessdate = 2022-07-14| date = June 2010| s2cid = 10239007| url = https://dl.acm.org/doi/10.1145/1743546.1743564| url-access = subscription}}</ref>
to describe that high performance in a specific ___domain requires both general and highly ___domain-specific knowledge. Ed Feigenbaum and Doug Lenat called this The Knowledge Principle:
{{Blockquote
|text=(1) The Knowledge Principle: if a program is to perform a complex task well, it must know a great deal about the world in which it operates.<br/>(2) A plausible extension of that principle, called the Breadth Hypothesis: there are two additional abilities necessary for intelligent behavior in unexpected situations: falling back on increasingly general knowledge, and analogizing to specific but far-flung knowledge.<ref name="Knowledge Principle">{{Cite
==== Success with expert systems ====
Line 94:
We did not have a grandiose vision. We worked bottom up. Our chemist was [[Carl Djerassi]], inventor of the chemical behind the birth control pill, and also one of the world's most respected mass spectrometrists. Carl and his postdocs were world-class experts in mass spectrometry. We began to add to their knowledge, inventing knowledge of engineering as we went along. These experiments amounted to titrating DENDRAL more and more knowledge. The more you did that, the smarter the program became. We had very good results.
The generalization was: in the knowledge lies the power. That was the big idea. In my career that is the huge, "Ah ha!," and it wasn't the way AI was being done previously. Sounds simple, but it's probably AI's most powerful generalization.<ref name="Feignebaum Interview">{{Cite journal| doi = 10.1145/1743546.1743564| issn = 0001-0782| volume = 53| issue = 6| pages = 41–45| last = Shustek| first = Len| title = An interview with Ed Feigenbaum| journal = Communications of the ACM| accessdate = 2022-08-05| date = 2010| s2cid = 10239007| url = https://cacm.acm.org/magazines/2010/6/92472-an-interview-with-ed-feigenbaum/fulltext| url-access = subscription}}</ref>}}
The other expert systems mentioned above came after DENDRAL. MYCIN exemplifies the classic expert system architecture of a knowledge-base of rules coupled to a symbolic reasoning mechanism, including the use of certainty factors to handle uncertainty. GUIDON shows how an explicit knowledge base can be repurposed for a second application, tutoring, and is an example of an [[intelligent tutoring system]], a particular kind of knowledge-based application. Clancey showed that it was not sufficient simply to use [[MYCIN]]'s rules for instruction, but that he also needed to add rules for dialogue management and student modeling.{{sfn|Clancey|1987}} XCON is significant because of the millions of dollars it saved [[Digital Equipment Corporation|DEC]], which triggered the expert system boom where most all major corporations in the US had expert systems groups, to capture corporate expertise, preserve it, and automate it:
Line 119:
Unfortunately, the AI boom did not last and Kautz best describes the second AI winter that followed:
{{Blockquote
|text=Many reasons can be offered for the arrival of the second AI winter. The hardware companies failed when much more cost-effective general Unix workstations from [[Sun Microsystems|Sun]] together with good compilers for LISP and Prolog came onto the market. Many commercial deployments of expert systems were discontinued when they proved too costly to maintain. Medical expert systems never caught on for several reasons: the difficulty in keeping them up to date; the challenge for medical professionals to learn how to use a bewildering variety of different expert systems for different medical conditions; and perhaps most crucially, the reluctance of doctors to trust a computer-made diagnosis over their gut instinct, even for specific domains where the expert systems could outperform an average doctor. Venture capital money deserted AI practically overnight. The world AI conference IJCAI hosted an enormous and lavish trade show and thousands of nonacademic attendees in 1987 in [[Vancouver]]; the main AI conference the following year, AAAI 1988 in [[St. Paul, Minnesota|St. Paul]], was a small and strictly academic affair.{{sfn|Kautz|2022|page=110}}
}}
Line 131 ⟶ 130:
One statistical approach, [[hidden Markov model]]s, had already been popularized in the 1980s for speech recognition work.{{sfn|Russell|Norvig|2021|p=25}} Subsequently, in 1988, [[Judea Pearl]] popularized the use of [[Bayesian Networks]] as a sound but efficient way of handling uncertain reasoning with his publication of the book Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference.{{sfn|Pearl|1988}} and Bayesian approaches were applied successfully in expert systems.{{sfn|Spiegelhalter |Dawid|Lauritzen|Cowell|1993}} Even later, in the 1990s, statistical relational learning, an approach that combines probability with logical formulas, allowed probability to be combined with first-order logic, e.g., with either [[Markov logic network|Markov Logic Networks]] or [[Probabilistic Soft Logic]].
Other, non-probabilistic extensions to first-order logic to support were also tried. For example, [[non-monotonic reasoning]] could be used with [[Reason maintenance|truth maintenance systems]]. A [[truth maintenance system]] tracked assumptions and justifications for all inferences. It allowed inferences to be withdrawn when assumptions were found out to be incorrect or a contradiction was derived. Explanations could be provided for an inference by [[Explainable artificial intelligence|explaining which rules were applied]] to create it and then continuing through underlying inferences and rules all the way back to root assumptions.{{sfn|Russell|Norvig|2021|pp=335-337}} [[
==== Machine learning ====
Line 146 ⟶ 145:
Advances were made in understanding machine learning theory, too. [[Tom M. Mitchell|Tom Mitchell]] introduced [[version space learning]] which describes learning as a search through a space of hypotheses, with upper, more general, and lower, more specific, boundaries encompassing all viable hypotheses consistent with the examples seen so far.<ref>{{harvc|in1=Michalski|in2=Carbonell|in3=Mitchell|year=1983 |c=Chapter 6: Learning by Experimentation: Acquiring and Refining Problem-Solving Heuristics |first1=Tom M. |last1=Mitchell |first2=Paul E. |last2=Utgoff |first3=Ranan |last3=Banerji}}</ref> More formally, [[Leslie Valiant|Valiant]] introduced [[Probably approximately correct learning|Probably Approximately Correct Learning]] (PAC Learning), a framework for the mathematical analysis of machine learning.<ref>{{Cite journal| doi = 10.1145/1968.1972| issn = 0001-0782| volume = 27| issue = 11| pages = 1134–1142| last = Valiant| first = L. G.| title = A theory of the learnable| journal = Communications of the ACM| date = 1984-11-05| s2cid = 12837541| doi-access = free}}</ref>
Symbolic machine learning encompassed more than learning by example. E.g., [[John Robert Anderson (psychologist)|John Anderson]] provided a [[cognitive model]] of human learning where skill practice results in a compilation of rules from a declarative format to a procedural format with his [[ACT-R]] [[cognitive architecture]]. For example, a student might learn to apply "Supplementary angles are two angles whose measures sum 180 degrees" as several different procedural rules. E.g., one rule might say that if X and Y are supplementary and you know X, then Y will be 180 - X. He called his approach "knowledge compilation". [[ACT-R]] has been used successfully to model aspects of human cognition, such as learning and retention. ACT-R is also used in [[intelligent tutoring systems]], called [[cognitive tutors]], to successfully teach geometry, computer programming, and algebra to school children.<ref "pump"="">{{Cite journal| volume = 8| pages = 30–43| last1 = Koedinger| first1 = K. R.| last2 = Anderson| first2 = J. R.| last3 = Hadley| first3 = W. H.| last4 = Mark| first4 = M. A.| last5 = others| title = Intelligent tutoring goes to school in the big city| journal = International Journal of Artificial Intelligence in Education
Inductive logic programming was another approach to learning that allowed logic programs to be synthesized from input-output examples. E.g., [[Ehud Shapiro]]'s MIS (Model Inference System) could synthesize Prolog programs from examples.<ref>{{Cite conference| conference = IJCAI| volume = 2| pages = 1064| last = Shapiro| first = Ehud Y| title = The Model Inference System| book-title = Proceedings of the 7th international joint conference on Artificial intelligence| date = 1981}}</ref> [[John R. Koza]] applied [[genetic algorithms]] to [[program synthesis]] to create [[genetic programming]], which he used to synthesize LISP programs. Finally, [[Zohar Manna]] and [[Richard Waldinger]] provided a more general approach to [[program synthesis]] that synthesizes a [[functional programming|functional program]] in the course of proving its specifications to be correct.<ref>{{Cite journal| doi = 10.1145/357084.357090| volume = 2| pages = 90–121| last1 = Manna| first1 = Zohar| last2 = Waldinger| first2 = Richard| title = A Deductive Approach to Program Synthesis| journal = ACM Trans. Program. Lang. Syst.| date = 1980-01-01| issue = 1| s2cid = 14770735}}</ref>
Line 154 ⟶ 153:
Symbolic machine learning was applied to learning concepts, rules, heuristics, and problem-solving. Approaches, other than those above, include:
# Learning from instruction or advice—i.e., taking human instruction, posed as advice, and determining how to operationalize it in specific situations. For example, in a game of Hearts, learning ''exactly how'' to play a hand to "avoid taking points."<ref>{{harvc|in1=Michalski|in2=Carbonell|in3=Mitchell|year=1983|c=Chapter 12: Machine Transformation of Advice into a Heuristic Search Procedure |first=David Jack |last=Mostow}}</ref>
# Learning from exemplars—improving performance by accepting subject-matter expert (SME) feedback during training. When problem-solving fails, querying the expert to either learn a new exemplar for problem-solving or to learn a new explanation as to exactly why one exemplar is more relevant than another. For example, the program Protos learned to diagnose tinnitus cases by interacting with an audiologist.<ref>{{harvc |in1=Michalski |in2=Carbonell |in3=Mitchell |year=1986 |pp=
# Learning by analogy—constructing problem solutions based on similar problems seen in the past, and then modifying their solutions to fit a new situation or ___domain.<ref>{{harvc |in1=Michalski |in2=Carbonell |in3=Mitchell |year=1983 |pp=
# Apprentice learning systems—learning novel solutions to problems by observing human problem-solving. Domain knowledge explains why novel solutions are correct and how the solution can be generalized. LEAP learned how to design VLSI circuits by observing human designers.<ref>{{harvc|in1=Kodratoff|in2=Michalski|year=1990|pp=
# Learning by discovery—i.e., creating tasks to carry out experiments and then learning from the results. [[Douglas Lenat|Doug Lenat]]'s [[Eurisko]], for example, learned heuristics to beat human players at the [[Traveller (role-playing game)|Traveller]] role-playing game for two years in a row.<ref>{{harvc|in1=Michalski|in2=Carbonell|in3=Mitchell|year=1983|pp=
# Learning macro-operators—i.e., searching for useful macro-operators to be learned from sequences of basic problem-solving actions. Good macro-operators simplify problem-solving by allowing problems to be solved at a more abstract level.<ref>{{Cite book| publisher = Pitman Publishing| isbn = 0-273-08690-1| last = Korf| first = Richard E.| title = Learning to Solve Problems by Searching for Macro-Operators| series = Research Notes in Artificial Intelligence| date = 1985}}</ref>
Line 165 ⟶ 164:
==== Neuro-symbolic AI: integrating neural and symbolic approaches ====
{{Main|Neuro-symbolic AI}}
Neuro-symbolic AI attempts to integrate neural and symbolic architectures in a manner that addresses strengths and weaknesses of each, in a complementary fashion, in order to support robust AI capable of reasoning, learning, and cognitive modeling. As argued by [[Leslie Valiant|Valiant]]{{sfn|Valiant|2008}} and many others,{{sfn|Garcez|Besold|De Raedt|Földiák|2015}} the effective construction of rich computational [[cognitive model]]s demands the combination of sound symbolic reasoning and efficient (machine) learning models. [[Gary Marcus]], similarly, argues that: "We cannot construct rich cognitive models in an adequate, automated way without the triumvirate of hybrid architecture, rich prior knowledge, and sophisticated techniques for reasoning.",{{sfn|Marcus|2020|p=44}} and in particular:
"To build a robust, knowledge-driven approach to AI we must have the machinery of symbol-manipulation in our toolkit. Too much of useful knowledge is abstract to make do without tools that represent and manipulate abstraction, and to date, the only machinery that we know of that can manipulate such abstract knowledge reliably is the apparatus of symbol
[[Henry Kautz]],{{sfn|Kautz|2020}} [[Francesca Rossi]],{{sfn|Rossi|2022}} and [[Bart Selman]]{{sfn|Selman|2022}} have also argued for a synthesis. Their arguments are based on a need to address the two kinds of thinking discussed in [[Daniel Kahneman]]'s book, ''[[Thinking, Fast and Slow]]''. Kahneman describes human thinking as having two components, [[Thinking, Fast and Slow#Two systems|System 1 and System 2]]. System 1 is fast, automatic, intuitive and unconscious. System 2 is slower, step-by-step, and explicit. System 1 is the kind used for pattern recognition while System 2 is far better suited for planning, deduction, and deliberative thinking. In this view, deep learning best models the first kind of thinking while symbolic reasoning best models the second kind and both are needed.
[[Artur Garcez|Garcez]] and Lamb describe research in this area as being ongoing for at least the past twenty years,{{sfn|Garcez|Lamb|2020|p=2}} dating from their 2002 book on neurosymbolic learning systems.{{sfn|Garcez|Broda|Gabbay|Gabbay|2002}} A series of workshops on neuro-symbolic reasoning has been held every year since 2005
In their 2015 paper, Neural-Symbolic Learning and Reasoning: Contributions and Challenges, Garcez et al. argue that:
Line 183:
* Neural|Symbolic—uses a neural architecture to interpret perceptual data as symbols and relationships that are then reasoned about symbolically.
* Neural:Symbolic → Neural—relies on symbolic reasoning to generate or label training data that is subsequently learned by a deep learning model, e.g., to train a neural model for symbolic computation by using a [[Macsyma]]-like symbolic mathematics system to create or label examples.
* Neural_{Symbolic}—uses a neural net that is generated from symbolic rules. An example is the Neural Theorem Prover,<ref>{{Cite conference| publisher = Association for Computational Linguistics| doi = 10.18653/v1/W16-1309| pages = 45–50| last1 = Rocktäschel| first1 = Tim| last2 = Riedel| first2 = Sebastian| title = Learning Knowledge Base Inference with Neural Theorem Provers| book-title = Proceedings of the 5th Workshop on Automated Knowledge Base Construction| ___location = San Diego, CA| accessdate = 2022-08-06| date = 2016| url = https://aclanthology.org/W16-1309| doi-access = free}}</ref> which constructs a neural network from an [[And–or tree|
* Neural[Symbolic]—allows a neural model to directly call a symbolic reasoning engine, e.g., to perform an action or evaluate a state.
Line 283:
Natural language processing focuses on treating language as data to perform tasks such as identifying topics without necessarily understanding the intended meaning. Natural language understanding, in contrast, constructs a meaning representation and uses that for further processing, such as answering questions.
[[Parsing]], [[Tokenization (lexical analysis)|tokenizing]], [[spell checker|spelling correction]], [[part-of-speech tagging]], [[shallow parsing|noun and verb phrase chunking]] are all aspects of natural language processing long handled by symbolic AI, but since improved by deep learning approaches. In symbolic AI, [[discourse representation theory]] and first-order logic have been used to represent sentence meanings. [[Latent semantic analysis]] (LSA) and [[explicit semantic analysis]] also provided vector representations of documents. In the latter case, vector components are interpretable as concepts named by Wikipedia articles.
New deep learning approaches based on [[Transformer (machine learning model)|Transformer models]] have now eclipsed these earlier symbolic AI approaches and attained state-of-the-art performance in natural language ''processing''. However, Transformer models are opaque and do not yet produce human-interpretable semantic representations for sentences and documents. Instead, they produce task-specific vectors where the meaning of the vector components is opaque.
Line 335:
Part of these disputes may be due to unclear terminology:
<blockquote>Turing award winner [[Judea Pearl]] offers a critique of machine learning which, unfortunately, conflates the terms machine learning and deep learning. Similarly, when Geoffrey Hinton refers to symbolic AI, the connotation of the term tends to be that of expert systems dispossessed of any ability to learn. The use of the terminology is in need of clarification. Machine learning is not confined to [[Association rule learning|association rule]] mining, c.f. the body of work on symbolic ML and relational learning (the differences to deep learning being the choice of representation, localist logical rather than distributed, and the non-use of [[gradient descent|gradient-based learning algorithms]]). Equally, symbolic AI is not just about [[Production system (computer science)|production rules]] written by hand. A proper definition of AI concerns [[knowledge representation and reasoning]], autonomous [[multi-agent system]]s, planning and [[Argumentation framework|argumentation]], as well as learning.{{sfn|Garcez|Lamb|2020|p=8}}</blockquote>It is worth noting that, from a theoretical perspective, the boundary of advantages between connectionist AI and symbolic AI may not be as clear-cut as it appears. For instance, Heng Zhang and his colleagues have proved that mainstream knowledge representation formalisms are recursively isomorphic, provided they are universal or have equivalent expressive power.<ref>{{Cite journal |last1=Zhang |first1=Heng |last2=Jiang |first2=Guifei |last3=Quan |first3=Donghui |date=2025-04-11 |title=A Theory of Formalisms for Representing Knowledge |url=https://ojs.aaai.org/index.php/AAAI/article/view/33674 |journal=Proceedings of the AAAI Conference on Artificial Intelligence |language=en |volume=39 |issue=14 |pages=15257–15264 |doi=10.1609/aaai.v39i14.33674 |issn=2374-3468|arxiv=2412.11855 }}</ref> This finding implies that there is no fundamental distinction between using symbolic or connectionist knowledge representation formalisms for the realization of [[artificial general intelligence]] (AGI). Moreover, the existence of recursive isomorphisms suggests that different technical approaches can draw insights from one another. From this perspective, it seems unnecessary to overemphasize the advantages of any single technical school; instead, mutual learning and integration may offer the most promising path toward the realization of AGI.
=== Situated robotics: the world as a model ===
Line 351:
== See also ==
{{div col|colwidth=
* [[Artificial intelligence]]
* [[Automated planning and scheduling]]
Line 393:
== References ==
* {{Cite journal| doi = 10.1016/0004-3702(91)90053-M| issn = 0004-3702| volume = 47| issue = 1| pages = 139–159| last = Brooks| first = Rodney A.| title = Intelligence without representation| journal = Artificial Intelligence| accessdate = 2022-09-13| date = 1991| s2cid = 207507849| url = https://dx.doi.org/10.1016/0004-3702%2891%2990053-M| url-access = subscription}}
* {{Cite book| title = Knowledge-Based Tutoring: The GUIDON Program (MIT Press Series in Artificial Intelligence)| last = Clancey | first = William |year = 1987| edition=Hardcover}}
* {{Crevier 1993}}.
Line 491:
* {{Citation| arxiv = 1606.04422| last1 = Serafini| first1 = Luciano| last2 = Garcez| first2 = Artur d'Avila| title = Logic Tensor Networks: Deep Learning and Logical Reasoning from Data and Knowledge| date = 2016-07-07}}
* {{cite journal |last1=Spiegelhalter |first1=David J. |last2=Dawid |first2=A. Philip |last3=Lauritzen |first3=Steffen |first4=Robert G. |last4=Cowell |author-link1=David Spiegelhalter |author-link3=Steffen Lauritzen |date=1993 |title=Bayesian analysis in expert systems |journal=Statistical Science |volume=8 |issue=3}}
* {{Cite journal |doi=10.1093/mind/LIX.236.433 |issn=0026-4423 |volume=LIX |issue=236 |pages=433–460 |last=Turing |first=A. M. |title=I.—Computing Machinery and Intelligence |journal=Mind |accessdate=2022-09-14 |date=1950 |url=https://doi.org/10.1093/mind/LIX.236.433|url-access=subscription }}
* {{Cite book| pages = 415–422| last = Valiant| first = Leslie G| chapter= Knowledge Infusion: In Pursuit of Robustness in Artificial Intelligence| date = 2008 |editor1=Hariharan, R. |editor2=Mukund, M. |editor3=Vinay, V. |title=Foundations of Software Technology and Theoretical Computer Science (Bangalore)}}
* {{cite
| year=2017
| author1=Xifan Yao | author2=Jiajun Zhou | author3=Jiangming Zhang | author4=Claudio R. Boer
| title=2017 5th International Conference on Enterprise Systems (ES) | chapter=From Intelligent Manufacturing to Smart Manufacturing for Industry 4.0 Driven by Next Generation Artificial Intelligence and Further
|doi=10.1109/es.2017.58
| isbn=978-1-5386-0936-1 }}
[[Category:Artificial intelligence]]
| |||