Symbolic artificial intelligence: Difference between revisions

Revision as of 23:53, 26 May 2025

Latest revision as of 10:56, 16 August 2025

(6 intermediate revisions by 4 users not shown)

Line 4:

is the term for the collection of all methods in artificial intelligence research that are based on high-level [[physical symbol systems hypothesis|symbolic]] (human-readable) representations of problems, [[Formal logic|logic]] and [[search algorithm|search]].<ref>{{Cite journal|last1=Garnelo|first1=Marta|last2=Shanahan|first2=Murray|date=2019-10-01|title=Reconciling deep learning with symbolic artificial intelligence: representing objects and relations|journal=Current Opinion in Behavioral Sciences|language=en|volume=29|pages=17–23|doi=10.1016/j.cobeha.2018.12.010|s2cid=72336067 |doi-access=free|hdl=10044/1/67796|hdl-access=free}}</ref> Symbolic AI used tools such as [[logic programming]], [[production (computer science)|production rules]], [[semantic nets]] and [[frame (artificial intelligence)|frames]], and it developed applications such as [[knowledge-based systems]] (in particular, [[expert systems]]), [[symbolic mathematics]], [[automated theorem provers]], [[ontologies]], the [[semantic web]], and [[automated planning and scheduling]] systems. The Symbolic AI paradigm led to seminal ideas in [[Artificial intelligence#Search and optimization|search]], [[symbolic programming]] languages, [[Intelligent agent|agents]], [[multi-agent systems]], the [[semantic web]], and the strengths and limitations of formal knowledge and [[automated reasoning|reasoning systems]].

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>{{Cite journal |lastlast1=Newell |firstfirst1=Allen |last2=Simon |first2=Herbert A. |date=1976-03-01 |title=Computer science as empirical inquiry: symbols and search |url=https://dl.acm.org/doi/10.1145/360018.360022 |journal=Commun. ACM |volume=19 |issue=3 |pages=113–126 |doi=10.1145/360018.360022 |issn=0001-0782}}</ref> An early boom, with early successes such as the [[Logic Theorist]] and [[Arthur Samuel (computer scientist)|Samuel]]'s [[Arthur Samuel (computer scientist)|Checkers Playing Program]], led to unrealistic expectations and promises and was followed by the first [[AI winter|AI Winter]] as funding dried up.{{sfn|Kautz|2022|pp=107-109}}{{sfn|Russell |Norvig|2021|p=19}} A second boom (1969–1986) occurred with the rise of expert systems, their promise of capturing corporate expertise, and an enthusiastic corporate embrace.{{sfn|Russell |Norvig|2021|pp=22-23}}{{sfn|Kautz|2022|pp=109-110}} That boom, and some early successes, e.g., with [[XCON]] at [[Digital Equipment Corporation|DEC]], was followed again by later disappointment.{{sfn|Kautz|2022|pp=109-110}} Problems with difficulties in knowledge acquisition, maintaining large knowledge bases, and brittleness in handling out-of-___domain problems arose. Another, second, AI Winter (1988–2011) followed.{{sfn|Kautz|2022|p=110}} Subsequently, AI researchers focused on addressing underlying problems in handling uncertainty and in knowledge acquisition.{{sfn|Kautz|2022|pp=110-111}} Uncertainty was addressed with formal methods such as [[hidden Markov model]]s, [[Bayesian reasoning]], and [[statistical relational learning]].{{sfn|Russell |Norvig|2021|p=25}}{{sfn|Kautz|2022|p=111}} Symbolic machine learning addressed the knowledge acquisition problem with contributions including [[Version space learning|Version Space]], [[Leslie Valiant|Valiant]]'s [[Probably approximately correct learning|PAC learning]], [[Ross Quinlan|Quinlan]]'s [[ID3 algorithm|ID3]] [[decision-tree]] learning, [[Case-based reasoning|case-based learning]], and [[inductive logic programming]] to learn relations.{{sfn|Kautz|2020|pp=110-111}}

[[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">

Line 72:

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 journalbook| last1=Lenat| first1=Douglas B| last2=Feigenbaum| first2=Edward A | title=On the thresholds of knowledge| journal=Proceedings of the International Workshop on Artificial Intelligence for Industrial Applications| chapter=On the thresholds of knowledge| date=1988| pages=291–300| doi=10.1109/AIIA.1988.13308| s2cid=11778085}}</ref>}}

==== Success with expert systems ====

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}}

{{sfn|Kautz|2022|page=110}}

}}

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=112-139112–139|c=Chapter 4: Protos: An Exemplar-Based Learning Apprentice |first=Ray |last=Bareiss|first2=Bruce|last2=Porter|first3=Craig|last3=Wier}}</ref>

# 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=137-162137–162|c=Chapter 5: Learning by Analogy: Formulating and Generalizing Plans from Past Experience |first=Jaime |last=Carbonell}}</ref><ref>{{harvc |in1=Michalski |in2=Carbonell |in3=Mitchell |year=1986 |pp=371-392371–392|c=Chapter 14: Derivational Analogy: A Theory of Reconstructive Problem Solving and Expertise Acquisition |first=Jaime |last=Carbonell}}</ref>

# 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=271-289271–289|c=Chapter 10: LEAP: A Learning Apprentice for VLSI Design |first=Tom |last=Mitchell|first2=Sridbar |last2=Mabadevan|first3=Louis|last3=Steinberg}}</ref>

# 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=243-306243–306|c=Chapter 9: The Role of Heuristics in Learning by Discovery: Three Case Studies|first=Douglas |last=Lenat}}</ref>

# 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:

Line 171:

[[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, see .<ref>http://www.neural-symbolic.org</ for details.ref>

In their 2015 paper, Neural-Symbolic Learning and Reasoning: Contributions and Challenges, Garcez et al. argue that:

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 |lastlast1=Zhang |firstfirst1=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=30em20em}}

* [[Artificial intelligence]]

* [[Automated planning and scheduling]]

Line 493:

* {{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 conferencebook

| 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 Onon | pages=311–318 |publisher=IEEE

|publisher=IEEE

|conference=2017 5th International Conference on Enterprise Systems (ES)

|doi=10.1109/es.2017.58

| isbn=978-1-5386-0936-1 }}

}}

[[Category:Artificial intelligence]]