Symbolic Artificial Intelligence

In synthetic intelligence, intelligence (likewise referred to as classical synthetic intelligence or logic-based synthetic intelligence) [1] [2] is the term for the collection of all techniques in expert system research study that are based on high-level symbolic (human-readable) representations of problems, reasoning and search. [3] Symbolic AI utilized tools such as reasoning programming, production guidelines, semantic internet and frames, and it established applications such as knowledge-based systems (in specific, expert systems), symbolic mathematics, automated theorem provers, ontologies, the semantic web, and automated planning and scheduling systems. The Symbolic AI paradigm led to influential concepts in search, symbolic programming languages, agents, multi-agent systems, the semantic web, and the strengths and constraints of formal understanding and reasoning systems.

Symbolic AI was the dominant paradigm of AI research study from the mid-1950s until the mid-1990s. [4] Researchers in the 1960s and the 1970s were encouraged that symbolic approaches would ultimately succeed in producing a machine with synthetic basic intelligence and considered this the supreme objective of their field. [citation required] An early boom, with early successes such as the Logic Theorist and Samuel’s Checkers Playing Program, resulted in unrealistic expectations and promises and was followed by the very first AI Winter as moneying dried up. [5] [6] A 2nd boom (1969-1986) accompanied the rise of professional systems, their guarantee of catching corporate knowledge, and an enthusiastic corporate embrace. [7] [8] That boom, and some early successes, e.g., with XCON at DEC, was followed again by later on frustration. [8] Problems with troubles in knowledge acquisition, keeping big knowledge bases, and brittleness in dealing with out-of-domain issues emerged. Another, 2nd, AI Winter (1988-2011) followed. [9] Subsequently, AI researchers concentrated on attending to hidden problems in handling unpredictability and in understanding acquisition. [10] Uncertainty was attended to with formal approaches such as concealed Markov designs, Bayesian thinking, and statistical relational learning. [11] [12] Symbolic machine finding out resolved the understanding acquisition issue with contributions including Version Space, Valiant’s PAC knowing, Quinlan’s ID3 decision-tree learning, case-based learning, and inductive reasoning shows to find out relations. [13]

Neural networks, a subsymbolic method, had actually been pursued from early days and reemerged highly in 2012. Early examples are Rosenblatt’s perceptron learning work, the backpropagation work of Rumelhart, Hinton and Williams, [14] and operate in convolutional neural networks by LeCun et al. in 1989. [15] However, neural networks were not viewed as effective until about 2012: “Until Big Data became prevalent, the general consensus in the Al community was that the so-called neural-network method was hopeless. Systems just didn’t work that well, compared to other methods. … A transformation can be found in 2012, when a variety of people, consisting of a group of scientists working with Hinton, worked out a method to utilize the power of GPUs to tremendously increase the power of neural networks.” [16] Over the next a number of years, deep knowing had magnificent success in handling vision, speech acknowledgment, speech synthesis, image generation, and machine translation. However, considering that 2020, as intrinsic problems with bias, description, coherence, and toughness ended up being more evident with deep learning methods; an increasing number of AI scientists have actually required integrating the very best of both the symbolic and neural network techniques [17] [18] and addressing areas that both approaches have trouble with, such as sensible reasoning. [16]

A short history of symbolic AI to today day follows listed below. Period and titles are drawn from Henry Kautz’s 2020 AAAI Robert S. Engelmore Memorial Lecture [19] and the longer Wikipedia article on the History of AI, with dates and titles differing a little for increased clarity.

The very first AI summer: irrational exuberance, 1948-1966

Success at early attempts in AI occurred in 3 primary areas: synthetic neural networks, understanding representation, and heuristic search, adding to high expectations. This section summarizes Kautz’s reprise of early AI history.

Approaches motivated by human or animal cognition or behavior

Cybernetic approaches tried to replicate the feedback loops between animals and their environments. A robotic turtle, with sensing units, motors for driving and steering, and seven vacuum tubes for control, based on a preprogrammed neural internet, was developed as early as 1948. This work can be seen as an early precursor to later operate in neural networks, support learning, and located robotics. [20]

An essential early symbolic AI program was the Logic theorist, written by Allen Newell, Herbert Simon and Cliff Shaw in 1955-56, as it had the ability to prove 38 elementary theorems from Whitehead and Russell’s Principia Mathematica. Newell, Simon, and Shaw later generalized this work to produce a domain-independent issue solver, GPS (General Problem Solver). GPS solved issues represented with official operators through state-space search using means-ends analysis. [21]

During the 1960s, symbolic methods accomplished great success at simulating smart behavior in structured environments such as game-playing, symbolic mathematics, and theorem-proving. AI research was focused in 4 organizations in the 1960s: Carnegie Mellon University, Stanford, MIT and (later on) University of Edinburgh. Every one established its own style of research. Earlier techniques based on cybernetics or synthetic neural networks were deserted or pushed into the background.

Herbert Simon and Allen Newell studied human problem-solving abilities and tried to formalize them, and their work laid the structures of the field of artificial intelligence, as well as cognitive science, operations research study and management science. Their research team utilized the results of psychological experiments to establish programs that simulated the methods that people used to solve issues. [22] [23] This custom, centered at Carnegie Mellon University would ultimately culminate in the development of the Soar architecture in the middle 1980s. [24] [25]

Heuristic search

In addition to the extremely specialized domain-specific sort of knowledge that we will see later on utilized in specialist systems, early symbolic AI scientists discovered another more general application of knowledge. These were called heuristics, guidelines that guide a search in promising directions: “How can non-enumerative search be useful when the underlying problem is greatly difficult? The technique promoted by Simon and Newell is to use heuristics: quick algorithms that may stop working on some inputs or output suboptimal options.” [26] Another crucial advance was to find a way to apply these heuristics that ensures an option will be discovered, if there is one, not standing up to the occasional fallibility of heuristics: “The A * algorithm offered a basic frame for complete and ideal heuristically directed search. A * is utilized as a subroutine within virtually every AI algorithm today however is still no magic bullet; its guarantee of efficiency is purchased the cost of worst-case rapid time. [26]

Early deal with knowledge representation and thinking

Early work covered both applications of formal reasoning stressing first-order logic, along with attempts to handle sensible thinking in a less formal manner.

Modeling formal reasoning with reasoning: the “neats”

Unlike Simon and Newell, John McCarthy felt that machines did not require to replicate the specific mechanisms of human thought, but could instead attempt to find the essence of abstract thinking and analytical with logic, [27] despite whether individuals utilized the exact same algorithms. [a] His laboratory at Stanford (SAIL) concentrated on using official reasoning to solve a wide array of issues, including understanding representation, preparation and learning. [31] Logic was also the focus of the work at the University of Edinburgh and somewhere else in Europe which caused the advancement of the programming language Prolog and the science of logic shows. [32] [33]

Modeling implicit sensible knowledge with frames and scripts: the “scruffies”

Researchers at MIT (such as Marvin Minsky and Seymour Papert) [34] [35] [6] discovered that solving hard issues in vision and natural language processing needed ad hoc solutions-they argued that no easy and basic concept (like logic) would catch all the elements of intelligent behavior. Roger Schank explained their “anti-logic” methods as “shabby” (instead of the “cool” paradigms at CMU and Stanford). [36] [37] Commonsense knowledge bases (such as Doug Lenat’s Cyc) are an example of “scruffy” AI, since they should be built by hand, one complex principle at a time. [38] [39] [40]

The very first AI winter: crushed dreams, 1967-1977

The very first AI winter was a shock:

During the first AI summer season, numerous individuals believed that device intelligence could be achieved in simply a couple of years. The Defense Advance Research Projects Agency (DARPA) launched programs to support AI research study to utilize AI to solve problems of nationwide security; in specific, to automate the translation of Russian to English for intelligence operations and to create self-governing tanks for the battleground. Researchers had begun to recognize that attaining AI was going to be much more difficult than was expected a decade earlier, however a mix of hubris and disingenuousness led numerous university and think-tank researchers to accept financing with pledges of deliverables that they must have understood they might not fulfill. By the mid-1960s neither useful natural language translation systems nor autonomous tanks had actually been produced, and a remarkable reaction embeded in. New DARPA management canceled existing AI financing programs.

Outside of the United States, the most fertile ground for AI research study was the UK. The AI winter in the UK was spurred on not a lot by disappointed military leaders as by rival academics who viewed AI scientists as charlatans and a drain on research study financing. A teacher of applied mathematics, Sir James Lighthill, was commissioned by Parliament to examine the state of AI research in the nation. The report mentioned that all of the issues being worked on in AI would be much better managed by scientists from other disciplines-such as applied mathematics. The report also declared that AI successes on toy problems could never ever scale to real-world applications due to combinatorial explosion. [41]

The second AI summer: understanding is power, 1978-1987

Knowledge-based systems

As constraints with weak, domain-independent techniques ended up being a growing number of evident, [42] researchers from all 3 customs started to build understanding into AI applications. [43] [7] The understanding revolution was driven by the realization that knowledge underlies high-performance, domain-specific AI applications.

Edward Feigenbaum said:

– “In the understanding lies the power.” [44]
to explain that high performance in a specific domain needs both basic and highly domain-specific understanding. Ed Feigenbaum and Doug Lenat called this The Knowledge Principle:

( 1) The Knowledge Principle: if a program is to carry out a complex task well, it must understand a fantastic offer about the world in which it runs.
( 2) A possible extension of that principle, called the Breadth Hypothesis: there are 2 additional capabilities essential for smart behavior in unexpected circumstances: drawing on increasingly general understanding, and analogizing to particular however distant knowledge. [45]

Success with expert systems

This “knowledge revolution” led to the advancement and deployment of specialist systems (introduced by Edward Feigenbaum), the very first commercially successful kind of AI software application. [46] [47] [48]

Key expert systems were:

DENDRAL, which discovered the structure of organic particles from their chemical formula and mass spectrometer readings.
MYCIN, which identified bacteremia – and suggested further lab tests, when needed – by translating laboratory outcomes, patient history, and medical professional observations. “With about 450 guidelines, MYCIN was able to perform as well as some specialists, and significantly much better than junior doctors.” [49] INTERNIST and CADUCEUS which tackled internal medicine medical diagnosis. Internist attempted to catch the know-how of the chairman of internal medication at the University of Pittsburgh School of Medicine while CADUCEUS might ultimately diagnose approximately 1000 different illness.
– GUIDON, which demonstrated how a knowledge base developed for professional issue solving could be repurposed for mentor. [50] XCON, to set up VAX computers, a then tiresome process that might use up to 90 days. XCON decreased the time to about 90 minutes. [9]
DENDRAL is thought about the very first professional system that relied on knowledge-intensive problem-solving. It is described below, by Ed Feigenbaum, from a Communications of the ACM interview, Interview with Ed Feigenbaum:

One of individuals at Stanford thinking about computer-based models of mind was Joshua Lederberg, the 1958 Nobel Prize winner in genes. When I told him I desired an induction “sandbox”, he stated, “I have simply the one for you.” His laboratory was doing mass spectrometry of amino acids. The concern was: how do you go from looking at the spectrum of an amino acid to the chemical structure of the amino acid? That’s how we began the DENDRAL Project: I was proficient at heuristic search approaches, and he had an algorithm that was great at creating the chemical problem area.

We did not have a grandiose vision. We worked bottom up. Our chemist was Carl Djerassi, developer of the chemical behind the contraceptive pill, and also one of the world’s most respected mass spectrometrists. Carl and his postdocs were world-class professionals in mass spectrometry. We started to include to their knowledge, inventing understanding of engineering as we went along. These experiments totaled up to titrating DENDRAL a growing number of understanding. The more you did that, the smarter the program became. We had excellent results.

The generalization was: in the understanding lies the power. That was the huge concept. In my profession that is the substantial, “Ah ha!,” and it wasn’t the method AI was being done previously. Sounds simple, but it’s probably AI‘s most powerful generalization. [51]

The other expert systems mentioned above came after DENDRAL. MYCIN exhibits the traditional professional system architecture of a knowledge-base of rules paired to a symbolic thinking system, consisting of the use of certainty aspects to manage unpredictability. GUIDON shows how a specific knowledge base can be repurposed for a second application, tutoring, and is an example of an intelligent tutoring system, a specific type of knowledge-based application. Clancey showed that it was not sufficient merely to utilize MYCIN’s guidelines for direction, but that he likewise required to include guidelines for dialogue management and student modeling. [50] XCON is substantial since of the countless dollars it saved DEC, which activated the professional system boom where most all significant corporations in the US had expert systems groups, to capture business expertise, maintain it, and automate it:

By 1988, DEC’s AI group had 40 professional systems released, with more on the method. DuPont had 100 in usage and 500 in advancement. Nearly every major U.S. corporation had its own Al group and was either using or examining professional systems. [49]

Chess professional knowledge was encoded in Deep Blue. In 1996, this permitted IBM’s Deep Blue, with the aid of symbolic AI, to win in a game of chess versus the world champ at that time, Garry Kasparov. [52]

Architecture of knowledge-based and skilled systems

A key element of the system architecture for all expert systems is the knowledge base, which stores facts and guidelines for analytical. [53] The easiest technique for a professional system knowledge base is simply a collection or network of production rules. Production rules link signs in a relationship similar to an If-Then statement. The professional system processes the guidelines to make deductions and to identify what extra details it requires, i.e. what concerns to ask, utilizing human-readable symbols. For instance, OPS5, CLIPS and their followers Jess and Drools run in this fashion.

Expert systems can operate in either a forward chaining – from evidence to conclusions – or backwards chaining – from goals to required data and requirements – manner. More innovative knowledge-based systems, such as Soar can likewise perform meta-level reasoning, that is reasoning about their own reasoning in regards to choosing how to resolve issues and keeping track of the success of problem-solving techniques.

Blackboard systems are a second type of knowledge-based or expert system architecture. They design a community of specialists incrementally contributing, where they can, to fix a problem. The problem is represented in multiple levels of abstraction or alternate views. The professionals (knowledge sources) volunteer their services whenever they acknowledge they can contribute. Potential analytical actions are represented on a program that is updated as the problem situation changes. A controller decides how useful each contribution is, and who should make the next analytical action. One example, the BB1 chalkboard architecture [54] was originally influenced by research studies of how human beings prepare to perform numerous tasks in a journey. [55] A development of BB1 was to use the same blackboard model to resolving its control issue, i.e., its controller carried out meta-level reasoning with knowledge sources that monitored how well a plan or the analytical was proceeding and could switch from one technique to another as conditions – such as objectives or times – altered. BB1 has been applied in several domains: building website planning, intelligent tutoring systems, and real-time client monitoring.

The 2nd AI winter season, 1988-1993

At the height of the AI boom, companies such as Symbolics, LMI, and Texas Instruments were offering LISP machines particularly targeted to speed up the advancement of AI applications and research. In addition, several expert system companies, such as Teknowledge and Inference Corporation, were offering expert system shells, training, and seeking advice from to corporations.

Unfortunately, the AI boom did not last and Kautz best describes the second AI winter season that followed:

Many factors can be used for the arrival of the second AI winter. The hardware companies stopped working when a lot more cost-efficient general Unix workstations from Sun together with good compilers for LISP and Prolog came onto the marketplace. Many commercial deployments of expert systems were stopped when they proved too costly to preserve. Medical professional systems never captured on for a number of reasons: the difficulty in keeping them as much as date; the challenge for physician to learn how to utilize an overwelming variety of various expert systems for different medical conditions; and possibly most crucially, the hesitation of medical professionals to trust a computer-made diagnosis over their gut impulse, even for particular domains where the professional systems might exceed a typical physician. Equity capital money deserted AI almost overnight. The world AI conference IJCAI hosted an enormous and lavish trade convention and thousands of nonacademic attendees in 1987 in Vancouver; the primary AI conference the list below year, AAAI 1988 in St. Paul, was a small and strictly scholastic affair. [9]

Adding in more strenuous foundations, 1993-2011

Uncertain thinking

Both analytical methods and extensions to logic were attempted.

One statistical method, hidden Markov designs, had already been popularized in the 1980s for speech acknowledgment work. [11] Subsequently, in 1988, Judea Pearl popularized making use of Bayesian Networks as a noise however effective way of managing unpredictable reasoning with his publication of the book Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. [56] and Bayesian techniques were used effectively in specialist systems. [57] Even later, in the 1990s, statistical relational learning, a technique that integrates possibility with sensible solutions, permitted likelihood to be integrated with first-order reasoning, e.g., with either Markov Logic Networks or Probabilistic Soft Logic.

Other, non-probabilistic extensions to first-order reasoning to assistance were likewise tried. For example, non-monotonic reasoning could be used with reality upkeep systems. A truth upkeep system tracked presumptions and validations for all inferences. It allowed reasonings to be withdrawn when presumptions were learnt to be inaccurate or a contradiction was derived. Explanations might be offered an inference by explaining which rules were applied to produce it and then continuing through underlying inferences and guidelines all the way back to root presumptions. [58] Lofti Zadeh had presented a various type of extension to manage the representation of ambiguity. For instance, in deciding how “heavy” or “tall” a guy is, there is frequently no clear “yes” or “no” response, and a predicate for heavy or tall would rather return values between 0 and 1. Those worths represented to what degree the predicates were real. His fuzzy logic even more provided a method for propagating mixes of these values through logical solutions. [59]

Artificial intelligence

Symbolic machine discovering approaches were examined to attend to the knowledge acquisition traffic jam. Among the earliest is Meta-DENDRAL. Meta-DENDRAL used a generate-and-test method to produce plausible rule hypotheses to evaluate against spectra. Domain and task understanding lowered the number of candidates evaluated to a manageable size. Feigenbaum explained Meta-DENDRAL as

… the conclusion of my imagine the early to mid-1960s relating to theory development. The conception was that you had an issue solver like DENDRAL that took some inputs and produced an output. In doing so, it utilized layers of understanding to guide and prune the search. That understanding acted due to the fact that we spoke with individuals. But how did the individuals get the knowledge? By taking a look at countless spectra. So we wanted a program that would look at countless spectra and presume the knowledge of mass spectrometry that DENDRAL could use to resolve private hypothesis development problems. We did it. We were even able to publish new knowledge of mass spectrometry in the Journal of the American Chemical Society, providing credit just in a footnote that a program, Meta-DENDRAL, really did it. We were able to do something that had been a dream: to have a computer system program created a new and publishable piece of science. [51]

In contrast to the knowledge-intensive approach of Meta-DENDRAL, Ross Quinlan created a domain-independent method to statistical classification, decision tree learning, beginning initially with ID3 [60] and after that later on extending its capabilities to C4.5. [61] The choice trees developed are glass box, interpretable classifiers, with human-interpretable classification rules.

Advances were made in comprehending artificial intelligence theory, too. Tom Mitchell presented version space learning which explains learning as a search through a space of hypotheses, with upper, more general, and lower, more specific, borders including all viable hypotheses consistent with the examples seen up until now. [62] More officially, Valiant introduced Probably Approximately Correct Learning (PAC Learning), a framework for the mathematical analysis of maker knowing. [63]

Symbolic device finding out incorporated more than finding out by example. E.g., John Anderson supplied a cognitive model of human learning where skill practice results in a compilation of guidelines from a declarative format to a procedural format with his ACT-R cognitive architecture. For example, a student may learn to use “Supplementary angles are 2 angles whose measures sum 180 degrees” as a number of various procedural rules. E.g., one guideline may state that if X and Y are extra and you know X, then Y will be 180 – X. He called his approach “understanding compilation”. ACT-R has actually been used effectively to design aspects of human cognition, such as learning and retention. ACT-R is likewise utilized in intelligent tutoring systems, called cognitive tutors, to successfully teach geometry, computer programming, and algebra to school kids. [64]

Inductive logic programs was another technique to learning that allowed logic programs to be manufactured from input-output examples. E.g., Ehud Shapiro’s MIS (Model Inference System) could synthesize Prolog programs from examples. [65] John R. Koza used genetic algorithms to program synthesis to produce hereditary programming, which he used to synthesize LISP programs. Finally, Zohar Manna and Richard Waldinger provided a more general approach to program synthesis that manufactures a practical program in the course of showing its requirements to be right. [66]

As an alternative to reasoning, Roger Schank presented case-based thinking (CBR). The CBR technique detailed in his book, Dynamic Memory, [67] focuses initially on keeping in mind essential analytical cases for future use and generalizing them where appropriate. When confronted with a new issue, CBR retrieves the most comparable previous case and adapts it to the specifics of the existing issue. [68] Another alternative to reasoning, genetic algorithms and hereditary programs are based on an evolutionary model of knowing, where sets of guidelines are encoded into populations, the guidelines govern the behavior of people, and selection of the fittest prunes out sets of unsuitable rules over numerous generations. [69]

Symbolic artificial intelligence was used to learning ideas, rules, heuristics, and analytical. Approaches, aside from those above, consist of:

1. Learning from instruction or advice-i.e., taking human direction, presented as recommendations, and determining how to operationalize it in particular circumstances. For example, in a game of Hearts, learning precisely how to play a hand to “prevent taking points.” [70] 2. Learning from exemplars-improving efficiency by accepting subject-matter specialist (SME) feedback throughout training. When analytical fails, querying the professional to either find out a new exemplar for problem-solving or to learn a brand-new description as to precisely why one prototype is more pertinent than another. For instance, the program Protos discovered to identify tinnitus cases by connecting with an audiologist. [71] 3. Learning by analogy-constructing problem options based on similar problems seen in the past, and then customizing their options to fit a brand-new situation or domain. [72] [73] 4. Apprentice learning systems-learning novel options to issues by observing human problem-solving. Domain understanding describes why unique services are correct and how the service can be generalized. LEAP learned how to develop VLSI circuits by observing human designers. [74] 5. Learning by discovery-i.e., creating tasks to perform experiments and after that finding out from the results. Doug Lenat’s Eurisko, for example, found out heuristics to beat human gamers at the Traveller role-playing video game for 2 years in a row. [75] 6. Learning macro-operators-i.e., looking for beneficial macro-operators to be gained from series of basic analytical actions. Good macro-operators streamline problem-solving by permitting problems to be solved at a more abstract level. [76]
Deep learning and neuro-symbolic AI 2011-now

With the increase of deep knowing, the symbolic AI method has actually been compared to deep knowing as complementary “… with parallels having actually been drawn many times by AI researchers in between Kahneman’s research study on human thinking and decision making – reflected in his book Thinking, Fast and Slow – and the so-called “AI systems 1 and 2″, which would in concept be designed by deep knowing and symbolic thinking, respectively.” In this view, symbolic reasoning is more apt for deliberative reasoning, planning, and description while deep learning is more apt for quick pattern acknowledgment in perceptual applications with noisy data. [17] [18]

Neuro-symbolic AI: incorporating neural and symbolic approaches

Neuro-symbolic AI efforts to integrate neural and symbolic architectures in a manner that addresses strengths and weaknesses of each, in a complementary style, in order to support robust AI capable of reasoning, finding out, and cognitive modeling. As argued by Valiant [77] and many others, [78] the reliable construction of rich computational cognitive models demands the combination of sound symbolic thinking and effective (maker) knowing designs. Gary Marcus, likewise, argues that: “We can not construct abundant cognitive models in a sufficient, automated method without the triune of hybrid architecture, rich anticipation, and sophisticated techniques for thinking.”, [79] and in specific: “To build a robust, knowledge-driven approach to AI we need to have the machinery of symbol-manipulation in our toolkit. Excessive of useful understanding is abstract to make do without tools that represent and control abstraction, and to date, the only equipment that we understand of that can control such abstract understanding dependably is the device of symbol adjustment. ” [80]

Henry Kautz, [19] Francesca Rossi, [81] and Bart Selman [82] have also argued for a synthesis. Their arguments are based on a need to deal with the 2 kinds of believing discussed in Daniel Kahneman’s book, Thinking, Fast and Slow. Kahneman explains human thinking as having two elements, System 1 and System 2. System 1 is fast, automated, user-friendly and unconscious. System 2 is slower, step-by-step, and explicit. System 1 is the kind utilized for pattern recognition while System 2 is far much better matched for planning, deduction, and deliberative thinking. In this view, deep learning best models the very first sort of thinking while symbolic reasoning best designs the 2nd kind and both are required.

Garcez and Lamb describe research study in this area as being continuous for at least the previous twenty years, [83] dating from their 2002 book on neurosymbolic knowing systems. [84] A series of workshops on neuro-symbolic thinking has actually been held every year considering that 2005, see http://www.neural-symbolic.org/ for details.

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

The combination of the symbolic and connectionist paradigms of AI has actually been pursued by a relatively little research neighborhood over the last twenty years and has actually yielded a number of considerable results. Over the last years, neural symbolic systems have been shown efficient in getting rid of the so-called propositional fixation of neural networks, as McCarthy (1988) put it in action to Smolensky (1988 ); see likewise (Hinton, 1990). Neural networks were revealed capable of representing modal and temporal reasonings (d’Avila Garcez and Lamb, 2006) and fragments of first-order logic (Bader, Hitzler, Hölldobler, 2008; d’Avila Garcez, Lamb, Gabbay, 2009). Further, neural-symbolic systems have been used to a variety of problems in the areas of bioinformatics, control engineering, software confirmation and adaptation, visual intelligence, ontology learning, and video game. [78]

Approaches for combination are varied. Henry Kautz’s taxonomy of neuro-symbolic architectures, together with some examples, follows:

– Symbolic Neural symbolic-is the existing approach of numerous neural designs in natural language processing, where words or subword tokens are both the supreme input and output of large language models. Examples include BERT, RoBERTa, and GPT-3.
– Symbolic [Neural] -is exemplified by AlphaGo, where symbolic methods are utilized to call neural methods. In this case the symbolic technique is Monte Carlo tree search and the neural methods find out how to assess video game positions.
– Neural|Symbolic-uses a neural architecture to analyze affective data as signs and relationships that are then reasoned about symbolically.
– Neural: Symbolic → Neural-relies on symbolic reasoning to generate or label training information that is subsequently found out by a deep learning design, e.g., to train a neural model for symbolic calculation by utilizing a Macsyma-like symbolic mathematics system to produce or label examples.
– Neural _ Symbolic -uses a neural net that is produced from symbolic guidelines. An example is the Neural Theorem Prover, [85] which constructs a neural network from an AND-OR proof tree produced from understanding base rules and terms. Logic Tensor Networks [86] likewise fall into this classification.
– Neural [Symbolic] -enables a neural design to directly call a symbolic reasoning engine, e.g., to perform an action or evaluate a state.

Many essential research study concerns remain, such as:

– What is the very best way to incorporate neural and symbolic architectures? [87]- How should symbolic structures be represented within neural networks and drawn out from them?
– How should sensible knowledge be discovered and reasoned about?
– How can abstract knowledge that is hard to encode logically be managed?

Techniques and contributions

This area offers a summary of methods and contributions in a total context resulting in lots of other, more detailed short articles in Wikipedia. Sections on Artificial Intelligence and Uncertain Reasoning are covered previously in the history section.

AI programs languages

The key AI programming language in the US during the last symbolic AI boom duration was LISP. LISP is the second oldest shows language after FORTRAN and was produced in 1958 by John McCarthy. LISP provided the very first read-eval-print loop to support rapid program advancement. Compiled functions could be easily blended with analyzed functions. Program tracing, stepping, and breakpoints were likewise provided, together with the ability to change worths or functions and continue from breakpoints or errors. It had the first self-hosting compiler, indicating that the compiler itself was originally composed in LISP and after that ran interpretively to assemble the compiler code.

Other essential developments pioneered by LISP that have spread out to other programs languages consist of:

Garbage collection
Dynamic typing
Higher-order functions
Recursion
Conditionals

Programs were themselves information structures that other programs might operate on, permitting the simple meaning of higher-level languages.

In contrast to the US, in Europe the crucial AI programs language during that exact same duration was Prolog. Prolog supplied a built-in store of truths and stipulations that might be queried by a read-eval-print loop. The store might function as an understanding base and the clauses could serve as guidelines or a limited type of logic. As a subset of first-order logic Prolog was based upon Horn provisions with a closed-world assumption-any realities not known were thought about false-and a special name presumption for primitive terms-e.g., the identifier barack_obama was considered to describe precisely one object. Backtracking and marriage are built-in to Prolog.

Alain Colmerauer and Philippe Roussel are credited as the innovators of Prolog. Prolog is a form of logic shows, which was developed by Robert Kowalski. Its history was likewise influenced by Carl Hewitt’s PLANNER, an assertional database with pattern-directed invocation of methods. For more detail see the section on the origins of Prolog in the PLANNER article.

Prolog is also a kind of declarative shows. The logic clauses that describe programs are straight translated to run the programs defined. No explicit series of actions is required, as is the case with necessary shows languages.

Japan promoted Prolog for its Fifth Generation Project, intending to construct unique hardware for high performance. Similarly, LISP machines were constructed to run LISP, however as the 2nd AI boom turned to bust these business might not complete with brand-new workstations that might now run LISP or Prolog natively at similar speeds. See the history section for more information.

Smalltalk was another influential AI shows language. For instance, it introduced metaclasses and, along with Flavors and CommonLoops, affected the Common Lisp Object System, or (CLOS), that is now part of Common Lisp, the present basic Lisp dialect. CLOS is a Lisp-based object-oriented system that permits multiple inheritance, in addition to incremental extensions to both classes and metaclasses, therefore providing a run-time meta-object procedure. [88]

For other AI programs languages see this list of shows languages for artificial intelligence. Currently, Python, a multi-paradigm programming language, is the most popular programs language, partly due to its extensive plan library that supports data science, natural language processing, and deep learning. Python includes a read-eval-print loop, functional elements such as higher-order functions, and object-oriented shows that consists of metaclasses.

Search

Search emerges in lots of kinds of issue fixing, including planning, constraint satisfaction, and playing games such as checkers, chess, and go. The best known AI-search tree search algorithms are breadth-first search, depth-first search, A *, and Monte Carlo Search. Key search algorithms for Boolean satisfiability are WalkSAT, conflict-driven provision learning, and the DPLL algorithm. For adversarial search when playing games, alpha-beta pruning, branch and bound, and minimax were early contributions.

Knowledge representation and thinking

Multiple different approaches to represent understanding and then reason with those representations have actually been examined. Below is a fast overview of techniques to knowledge representation and automated thinking.

Knowledge representation

Semantic networks, conceptual charts, frames, and logic are all methods to modeling understanding such as domain understanding, problem-solving knowledge, and the semantic meaning of language. Ontologies design key concepts and their relationships in a domain. Example ontologies are YAGO, WordNet, and DOLCE. DOLCE is an example of an upper ontology that can be used for any domain while WordNet is a lexical resource that can likewise be deemed an ontology. YAGO integrates WordNet as part of its ontology, to line up realities drawn out from Wikipedia with WordNet synsets. The Disease Ontology is an example of a medical ontology currently being utilized.

Description logic is a reasoning for automated category of ontologies and for identifying inconsistent classification data. OWL is a language used to represent ontologies with description reasoning. Protégé is an ontology editor that can check out in OWL ontologies and after that check consistency with deductive classifiers such as such as HermiT. [89]

First-order logic is more basic than description reasoning. The automated theorem provers discussed below can prove theorems in first-order logic. Horn provision logic is more limited than first-order reasoning and is used in reasoning programming languages such as Prolog. Extensions to first-order logic consist of temporal reasoning, to handle time; epistemic logic, to reason about representative understanding; modal logic, to manage possibility and necessity; and probabilistic reasonings to manage logic and possibility together.

Automatic theorem showing

Examples of automated theorem provers for first-order logic are:

Prover9.
ACL2.
Vampire.

Prover9 can be utilized in conjunction with the Mace4 design checker. ACL2 is a theorem prover that can manage proofs by induction and is a descendant of the Boyer-Moore Theorem Prover, likewise called Nqthm.

Reasoning in knowledge-based systems

Knowledge-based systems have a specific understanding base, normally of rules, to enhance reusability across domains by separating procedural code and domain understanding. A separate inference engine procedures guidelines and includes, deletes, or modifies an understanding shop.

Forward chaining inference engines are the most typical, and are seen in CLIPS and OPS5. Backward chaining takes place in Prolog, where a more restricted logical representation is used, Horn Clauses. Pattern-matching, particularly marriage, is utilized in Prolog.

A more versatile type of analytical occurs when reasoning about what to do next occurs, rather than merely selecting among the available actions. This kind of meta-level reasoning is utilized in Soar and in the BB1 blackboard architecture.

Cognitive architectures such as ACT-R may have additional capabilities, such as the ability to put together often utilized knowledge into higher-level chunks.

Commonsense reasoning

Marvin Minsky first proposed frames as a way of analyzing common visual circumstances, such as a workplace, and Roger Schank extended this concept to scripts for typical regimens, such as eating in restaurants. Cyc has attempted to capture helpful common-sense knowledge and has “micro-theories” to handle specific type of domain-specific thinking.

Qualitative simulation, such as Benjamin Kuipers’s QSIM, [90] approximates human reasoning about ignorant physics, such as what happens when we heat a liquid in a pot on the stove. We expect it to heat and potentially boil over, although we might not understand its temperature level, its boiling point, or other information, such as air pressure.

Similarly, Allen’s temporal period algebra is a simplification of thinking about time and Region Connection Calculus is a simplification of thinking about spatial relationships. Both can be solved with restraint solvers.

Constraints and constraint-based thinking

Constraint solvers carry out a more minimal type of inference than first-order reasoning. They can simplify sets of spatiotemporal restraints, such as those for RCC or Temporal Algebra, along with fixing other sort of puzzle problems, such as Wordle, Sudoku, cryptarithmetic problems, and so on. Constraint reasoning programming can be utilized to resolve scheduling issues, for example with restriction dealing with guidelines (CHR).

Automated preparation

The General Problem Solver (GPS) cast preparation as problem-solving utilized means-ends analysis to produce plans. STRIPS took a different technique, seeing planning as theorem proving. Graphplan takes a least-commitment method to planning, instead of sequentially choosing actions from a preliminary state, working forwards, or a goal state if working backwards. Satplan is a method to preparing where a preparation problem is decreased to a Boolean satisfiability issue.

Natural language processing

Natural language processing concentrates on dealing with language as information to carry out jobs such as recognizing topics without always comprehending the desired significance. Natural language understanding, on the other hand, constructs a meaning representation and uses that for further processing, such as answering questions.

Parsing, tokenizing, spelling correction, part-of-speech tagging, noun and verb phrase chunking are all elements of natural language processing long handled by symbolic AI, but since enhanced by deep learning methods. In symbolic AI, discourse representation theory and first-order reasoning have actually been utilized to represent sentence meanings. Latent semantic analysis (LSA) and explicit semantic analysis also supplied vector representations of files. In the latter case, vector elements are interpretable as concepts called by Wikipedia posts.

New deep learning techniques based on Transformer models have now eclipsed these earlier symbolic AI techniques and achieved modern efficiency in natural language processing. However, Transformer models are nontransparent and do not yet produce human-interpretable semantic representations for sentences and documents. Instead, they produce task-specific vectors where the significance of the vector parts is opaque.

Agents and multi-agent systems

Agents are autonomous systems embedded in an environment they view and act upon in some sense. Russell and Norvig’s standard textbook on synthetic intelligence is organized to reflect representative architectures of increasing elegance. [91] The elegance of representatives differs from simple reactive agents, to those with a model of the world and automated preparation capabilities, possibly a BDI representative, i.e., one with beliefs, desires, and intentions – or additionally a reinforcement learning model found out with time to choose actions – up to a combination of alternative architectures, such as a neuro-symbolic architecture [87] that includes deep knowing for perception. [92]

On the other hand, a multi-agent system consists of several agents that interact amongst themselves with some inter-agent interaction language such as Knowledge Query and Manipulation Language (KQML). The agents require not all have the very same internal architecture. Advantages of multi-agent systems include the capability to divide work among the representatives and to increase fault tolerance when agents are lost. Research problems include how representatives reach consensus, distributed problem solving, multi-agent learning, multi-agent preparation, and distributed restriction optimization.

Controversies occurred from early on in symbolic AI, both within the field-e.g., between logicists (the pro-logic “neats”) and non-logicists (the anti-logic “scruffies”)- and between those who welcomed AI but rejected symbolic approaches-primarily connectionists-and those outside the field. Critiques from outside of the field were mainly from theorists, on intellectual premises, but also from financing firms, specifically throughout the 2 AI winter seasons.

The Frame Problem: understanding representation obstacles for first-order logic

Limitations were found in using simple first-order logic to reason about vibrant domains. Problems were found both with concerns to mentioning the preconditions for an action to succeed and in providing axioms for what did not alter after an action was performed.

McCarthy and Hayes introduced the Frame Problem in 1969 in the paper, “Some Philosophical Problems from the Standpoint of Artificial Intelligence.” [93] A simple example occurs in “proving that one person could get into discussion with another”, as an axiom asserting “if a person has a telephone he still has it after searching for a number in the telephone directory” would be required for the reduction to succeed. Similar axioms would be needed for other domain actions to define what did not change.

A comparable issue, called the Qualification Problem, happens in trying to enumerate the preconditions for an action to be successful. An infinite variety of pathological conditions can be imagined, e.g., a banana in a tailpipe might avoid a vehicle from operating correctly.

McCarthy’s method to fix the frame issue was circumscription, a kind of non-monotonic logic where deductions might be made from actions that need just define what would alter while not having to clearly define whatever that would not alter. Other non-monotonic reasonings provided truth upkeep systems that modified beliefs resulting in contradictions.

Other ways of managing more open-ended domains included probabilistic reasoning systems and artificial intelligence to discover brand-new concepts and rules. McCarthy’s Advice Taker can be viewed as an inspiration here, as it might include new knowledge supplied by a human in the form of assertions or rules. For example, experimental symbolic machine finding out systems checked out the ability to take high-level natural language recommendations and to interpret it into domain-specific actionable rules.

Similar to the issues in handling vibrant domains, common-sense thinking is also challenging to capture in formal thinking. Examples of common-sense reasoning consist of implicit reasoning about how people think or basic understanding of day-to-day occasions, items, and living creatures. This kind of understanding is taken for granted and not deemed noteworthy. Common-sense thinking is an open area of research and challenging both for symbolic systems (e.g., Cyc has tried to record crucial parts of this understanding over more than a years) and neural systems (e.g., self-driving vehicles that do not understand not to drive into cones or not to hit pedestrians strolling a bike).

McCarthy viewed his Advice Taker as having sensible, however his meaning of common-sense was different than the one above. [94] He defined a program as having sound judgment “if it immediately deduces for itself a sufficiently large class of instant consequences of anything it is told and what it currently knows. “

Connectionist AI: philosophical obstacles and sociological conflicts

Connectionist methods include earlier work on neural networks, [95] such as perceptrons; operate in the mid to late 80s, such as Danny Hillis’s Connection Machine and Yann LeCun’s advances in convolutional neural networks; to today’s advanced methods, such as Transformers, GANs, and other work in deep learning.

Three philosophical positions [96] have been laid out among connectionists:

1. Implementationism-where connectionist architectures carry out the abilities for symbolic processing,
2. Radical connectionism-where symbolic processing is declined absolutely, and connectionist architectures underlie intelligence and are completely adequate to describe it,
3. Moderate connectionism-where symbolic processing and connectionist architectures are viewed as complementary and both are needed for intelligence

Olazaran, in his sociological history of the controversies within the neural network neighborhood, described the moderate connectionism consider as basically compatible with existing research study in neuro-symbolic hybrids:

The 3rd and last position I wish to take a look at here is what I call the moderate connectionist view, a more eclectic view of the current debate between connectionism and symbolic AI. Among the researchers who has elaborated this position most explicitly is Andy Clark, a philosopher from the School of Cognitive and Computing Sciences of the University of Sussex (Brighton, England). Clark protected hybrid (partly symbolic, partly connectionist) systems. He declared that (a minimum of) two sort of theories are required in order to study and model cognition. On the one hand, for some information-processing jobs (such as pattern acknowledgment) connectionism has advantages over symbolic designs. But on the other hand, for other cognitive procedures (such as serial, deductive thinking, and generative sign adjustment processes) the symbolic paradigm offers adequate designs, and not only “approximations” (contrary to what radical connectionists would claim). [97]

Gary Marcus has declared that the animus in the deep knowing community versus symbolic approaches now might be more sociological than philosophical:

To think that we can simply desert symbol-manipulation is to suspend shock.

And yet, for the many part, that’s how most present AI earnings. Hinton and numerous others have striven to banish signs altogether. The deep learning hope-seemingly grounded not so much in science, however in a sort of historic grudge-is that smart behavior will emerge purely from the confluence of massive information and deep learning. Where classical computer systems and software application solve jobs by specifying sets of symbol-manipulating guidelines committed to particular tasks, such as modifying a line in a word processor or carrying out a calculation in a spreadsheet, neural networks generally attempt to solve tasks by statistical approximation and gaining from examples.

According to Marcus, Geoffrey Hinton and his coworkers have been vehemently “anti-symbolic”:

When deep knowing reemerged in 2012, it was with a type of take-no-prisoners attitude that has actually characterized the majority of the last years. By 2015, his hostility toward all things signs had completely taken shape. He gave a talk at an AI workshop at Stanford comparing symbols to aether, among science’s greatest mistakes.

…

Since then, his anti-symbolic project has actually just increased in strength. In 2016, Yann LeCun, Bengio, and Hinton composed a manifesto for deep learning in one of science’s essential journals, Nature. It closed with a direct attack on symbol manipulation, calling not for reconciliation however for outright replacement. Later, Hinton told an event of European Union leaders that investing any further cash in symbol-manipulating methods was “a substantial mistake,” likening it to purchasing internal combustion engines in the period of electrical cars and trucks. [98]

Part of these disagreements may be because of unclear terminology:

Turing award winner Judea Pearl offers a critique of maker knowing which, unfortunately, conflates the terms artificial intelligence and deep knowing. Similarly, when Geoffrey Hinton describes symbolic AI, the connotation of the term tends to be that of professional systems dispossessed of any ability to discover. Using the terminology is in requirement of information. Artificial intelligence is not restricted to association guideline mining, c.f. the body of work on symbolic ML and relational learning (the differences to deep knowing being the choice of representation, localist rational rather than distributed, and the non-use of gradient-based learning algorithms). Equally, symbolic AI is not simply about production guidelines written by hand. An appropriate definition of AI issues knowledge representation and reasoning, autonomous multi-agent systems, planning and argumentation, as well as knowing. [99]

Situated robotics: the world as a design

Another critique of symbolic AI is the embodied cognition technique:

The embodied cognition method declares that it makes no sense to consider the brain independently: cognition occurs within a body, which is embedded in an environment. We need to study the system as a whole; the brain’s working exploits regularities in its environment, including the rest of its body. Under the embodied cognition method, robotics, vision, and other sensors become main, not peripheral. [100]

Rodney Brooks created behavior-based robotics, one technique to embodied cognition. Nouvelle AI, another name for this approach, is viewed as an alternative to both symbolic AI and connectionist AI. His approach declined representations, either symbolic or dispersed, as not only unneeded, however as destructive. Instead, he developed the subsumption architecture, a layered architecture for embodied representatives. Each layer attains a various purpose and should work in the real life. For instance, the first robot he describes in Intelligence Without Representation, has three layers. The bottom layer analyzes sonar sensing units to avoid things. The middle layer triggers the robotic to wander around when there are no challenges. The top layer causes the robot to go to more far-off places for more exploration. Each layer can temporarily hinder or reduce a lower-level layer. He criticized AI researchers for specifying AI problems for their systems, when: “There is no tidy division between understanding (abstraction) and reasoning in the genuine world.” [101] He called his robotics “Creatures” and each layer was “composed of a fixed-topology network of basic finite state machines.” [102] In the Nouvelle AI technique, “First, it is essential to evaluate the Creatures we integrate in the genuine world; i.e., in the same world that we human beings occupy. It is disastrous to fall under the temptation of testing them in a streamlined world first, even with the finest intentions of later transferring activity to an unsimplified world.” [103] His emphasis on real-world testing remained in contrast to “Early operate in AI focused on video games, geometrical issues, symbolic algebra, theorem proving, and other official systems” [104] and using the blocks world in symbolic AI systems such as SHRDLU.

Current views

Each approach-symbolic, connectionist, and behavior-based-has advantages, but has actually been criticized by the other methods. Symbolic AI has been slammed as disembodied, responsible to the certification problem, and poor in managing the perceptual issues where deep finding out excels. In turn, connectionist AI has been criticized as poorly matched for deliberative detailed issue solving, including understanding, and dealing with preparation. Finally, Nouvelle AI masters reactive and real-world robotics domains but has actually been slammed for troubles in including knowing and knowledge.

Hybrid AIs incorporating several of these methods are presently deemed the course forward. [19] [81] [82] Russell and Norvig conclude that:

Overall, Dreyfus saw locations where AI did not have complete answers and stated that Al is for that reason difficult; we now see much of these exact same areas undergoing ongoing research study and advancement leading to increased capability, not impossibility. [100]

Expert system.
Automated planning and scheduling
Automated theorem proving
Belief revision
Case-based reasoning
Cognitive architecture
Cognitive science
Connectionism
Constraint programs
Deep learning
First-order reasoning
GOFAI
History of artificial intelligence
Inductive logic programming
Knowledge-based systems
Knowledge representation and thinking
Logic programs
Artificial intelligence
Model monitoring
Model-based thinking
Multi-agent system
Natural language processing
Neuro-symbolic AI
Ontology
Philosophy of expert system
Physical symbol systems hypothesis
Semantic Web
Sequential pattern mining
Statistical relational learning
Symbolic mathematics
YAGO ontology
WordNet

Notes

^ McCarthy once stated: “This is AI, so we don’t care if it’s emotionally genuine”. [4] McCarthy reiterated his position in 2006 at the AI@50 conference where he stated “Expert system is not, by meaning, simulation of human intelligence”. [28] Pamela McCorduck writes that there are “2 significant branches of artificial intelligence: one focused on producing smart habits regardless of how it was accomplished, and the other focused on modeling intelligent processes discovered in nature, especially human ones.”, [29] Stuart Russell and Peter Norvig composed “Aeronautical engineering texts do not define the goal of their field as making ‘machines that fly so precisely like pigeons that they can trick even other pigeons.'” [30] Citations

^ Garnelo, Marta; Shanahan, Murray (October 2019). “Reconciling deep learning with symbolic artificial intelligence: representing items and relations”. Current Opinion in Behavioral Sciences. 29: 17-23. doi:10.1016/ j.cobeha.2018.12.010. hdl:10044/ 1/67796.
^ Thomason, Richmond (February 27, 2024). “Logic-Based Artificial Intelligence”. In Zalta, Edward N. (ed.). Stanford Encyclopedia of Philosophy.
^ Garnelo, Marta; Shanahan, Murray (2019-10-01). “Reconciling deep learning with symbolic expert system: representing objects and relations”. Current Opinion in Behavioral Sciences. 29: 17-23. doi:10.1016/ j.cobeha.2018.12.010. hdl:10044/ 1/67796. S2CID 72336067.
^ a b Kolata 1982.
^ Kautz 2022, pp. 107-109.
^ a b Russell & Norvig 2021, p. 19.
^ a b Russell & Norvig 2021, pp. 22-23.
^ a b Kautz 2022, pp. 109-110.
^ a b c Kautz 2022, p. 110.
^ Kautz 2022, pp. 110-111.
^ a b Russell & Norvig 2021, p. 25.
^ Kautz 2022, p. 111.
^ Kautz 2020, pp. 110-111.
^ Rumelhart, David E.; Hinton, Geoffrey E.; Williams, Ronald J. (1986 ). “Learning representations by back-propagating mistakes”. Nature. 323 (6088 ): 533-536. Bibcode:1986 Natur.323..533 R. doi:10.1038/ 323533a0. ISSN 1476-4687. S2CID 205001834.
^ LeCun, Y.; Boser, B.; Denker, I.; Henderson, D.; Howard, R.; Hubbard, W.; Tackel, L. (1989 ). “Backpropagation Applied to Handwritten Zip Code Recognition”. Neural Computation. 1 (4 ): 541-551. doi:10.1162/ neco.1989.1.4.541. S2CID 41312633.
^ a b Marcus & Davis 2019.
^ a b Rossi, Francesca. “Thinking Fast and Slow in AI”. AAAI. Retrieved 5 July 2022.
^ a b Selman, Bart. “AAAI Presidential Address: The State of AI”. AAAI. Retrieved 5 July 2022.
^ a b c Kautz 2020.
^ Kautz 2022, p. 106.
^ Newell & Simon 1972.
^ & McCorduck 2004, pp. 139-179, 245-250, 322-323 (EPAM).
^ Crevier 1993, pp. 145-149.
^ McCorduck 2004, pp. 450-451.
^ Crevier 1993, pp. 258-263.
^ a b Kautz 2022, p. 108.
^ Russell & Norvig 2021, p. 9 (logicist AI), p. 19 (McCarthy’s work).
^ Maker 2006.
^ McCorduck 2004, pp. 100-101.
^ Russell & Norvig 2021, p. 2.
^ McCorduck 2004, pp. 251-259.
^ Crevier 1993, pp. 193-196.
^ Howe 1994.
^ McCorduck 2004, pp. 259-305.
^ Crevier 1993, pp. 83-102, 163-176.
^ McCorduck 2004, pp. 421-424, 486-489.
^ Crevier 1993, p. 168.
^ McCorduck 2004, p. 489.
^ Crevier 1993, pp. 239-243.
^ Russell & Norvig 2021, p. 316, 340.
^ Kautz 2022, p. 109.
^ Russell & Norvig 2021, p. 22.
^ McCorduck 2004, pp. 266-276, 298-300, 314, 421.
^ Shustek, Len (June 2010). “An interview with Ed Feigenbaum”. Communications of the ACM. 53 (6 ): 41-45. doi:10.1145/ 1743546.1743564. ISSN 0001-0782. S2CID 10239007. Retrieved 2022-07-14.
^ Lenat, Douglas B; Feigenbaum, Edward A (1988 ). “On the thresholds of knowledge”. Proceedings of the International Workshop on Artificial Intelligence for Industrial Applications: 291-300. doi:10.1109/ AIIA.1988.13308. S2CID 11778085.
^ Russell & Norvig 2021, pp. 22-24.
^ McCorduck 2004, pp. 327-335, 434-435.
^ Crevier 1993, pp. 145-62, 197-203.
^ a b Russell & Norvig 2021, p. 23.
^ a b Clancey 1987.
^ a b Shustek, Len (2010 ). “An interview with Ed Feigenbaum”. Communications of the ACM. 53 (6 ): 41-45. doi:10.1145/ 1743546.1743564. ISSN 0001-0782. S2CID 10239007. Retrieved 2022-08-05.
^ “The fascination with AI: what is expert system?”. IONOS Digitalguide. Retrieved 2021-12-02.
^ Hayes-Roth, Murray & Adelman 2015.
^ Hayes-Roth, Barbara (1985 ). “A blackboard architecture for control”. Expert system. 26 (3 ): 251-321. doi:10.1016/ 0004-3702( 85 )90063-3.
^ Hayes-Roth, Barbara (1980 ). Human Planning Processes. RAND.
^ Pearl 1988.
^ Spiegelhalter et al. 1993.
^ Russell & Norvig 2021, pp. 335-337.
^ Russell & Norvig 2021, p. 459.
^ Quinlan, J. Ross. “Chapter 15: Learning Efficient Classification Procedures and their Application to Chess End Games”. In Michalski, Carbonell & Mitchell (1983 ).
^ Quinlan, J. Ross (1992-10-15). C4.5: Programs for Machine Learning (1st ed.). San Mateo, Calif: Morgan Kaufmann. ISBN 978-1-55860-238-0.
^ Mitchell, Tom M.; Utgoff, Paul E.; Banerji, Ranan. “Chapter 6: Learning by Experimentation: Acquiring and Refining Problem-Solving Heuristics”. In Michalski, Carbonell & Mitchell (1983 ).
^ Valiant, L. G. (1984-11-05). “A theory of the learnable”. Communications of the ACM. 27 (11 ): 1134-1142. doi:10.1145/ 1968.1972. ISSN 0001-0782. S2CID 12837541.
^ Koedinger, K. R.; Anderson, J. R.; Hadley, W. H.; Mark, M. A.; others (1997 ). “Intelligent tutoring goes to school in the huge city”. International Journal of Expert System in Education (IJAIED). 8: 30-43. Retrieved 2012-08-18.
^ Shapiro, Ehud Y (1981 ). “The Model Inference System”. Proceedings of the 7th worldwide joint conference on Expert system. IJCAI. Vol. 2. p. 1064.
^ Manna, Zohar; Waldinger, Richard (1980-01-01). “A Deductive Approach to Program Synthesis”. ACM Trans. Program. Lang. Syst. 2 (1 ): 90-121. doi:10.1145/ 357084.357090. S2CID 14770735.
^ Schank, Roger C. (1983-01-28). Dynamic Memory: A Theory of Reminding and Learning in Computers and People. Cambridge Cambridgeshire: New York: Cambridge University Press. ISBN 978-0-521-27029-8.
^ Hammond, Kristian J. (1989-04-11). Case-Based Planning: Viewing Planning as a Memory Task. Boston: Academic Press. ISBN 978-0-12-322060-8.
^ Koza, John R. (1992-12-11). Genetic Programming: On the Programming of Computers by Means of Natural Selection (1st ed.). Cambridge, Mass: A Bradford Book. ISBN 978-0-262-11170-6.
^ Mostow, David Jack. “Chapter 12: Machine Transformation of Advice into a Heuristic Search Procedure”. In Michalski, Carbonell & Mitchell (1983 ).
^ Bareiss, Ray; Porter, Bruce; Wier, Craig. “Chapter 4: Protos: An Exemplar-Based Learning Apprentice”. In Michalski, Carbonell & Mitchell (1986 ), pp. 112-139.
^ Carbonell, Jaime. “Chapter 5: Learning by Analogy: Formulating and Generalizing Plans from Past Experience”. In Michalski, Carbonell & Mitchell (1983 ), pp. 137-162.
^ Carbonell, Jaime. “Chapter 14: Derivational Analogy: A Theory of Reconstructive Problem Solving and Expertise Acquisition”. In Michalski, Carbonell & Mitchell (1986 ), pp. 371-392.
^ Mitchell, Tom; Mabadevan, Sridbar; Steinberg, Louis. “Chapter 10: LEAP: A Learning Apprentice for VLSI Design”. In Kodratoff & Michalski (1990 ), pp. 271-289.
^ Lenat, Douglas. “Chapter 9: The Role of Heuristics in Learning by Discovery: Three Case Studies”. In Michalski, Carbonell & Mitchell (1983 ), pp. 243-306.
^ Korf, Richard E. (1985 ). Learning to Solve Problems by Searching for Macro-Operators. Research Notes in Expert System. Pitman Publishing. ISBN 0-273-08690-1.
^ Valiant 2008.
^ a b Garcez et al. 2015.
^ Marcus 2020, p. 44.
^ Marcus 2020, p. 17.
^ a b Rossi 2022.
^ a b Selman 2022.
^ Garcez & Lamb 2020, p. 2.
^ Garcez et al. 2002.
^ Rocktäschel, Tim; Riedel, Sebastian (2016 ). “Learning Knowledge Base Inference with Neural Theorem Provers”. Proceedings of the 5th Workshop on Automated Knowledge Base Construction. San Diego, CA: Association for Computational Linguistics. pp. 45-50. doi:10.18653/ v1/W16 -1309. Retrieved 2022-08-06.
^ Serafini, Luciano; Garcez, Artur d’Avila (2016 ), Logic Tensor Networks: Deep Learning and Logical Reasoning from Data and Knowledge, arXiv:1606.04422.
^ a b Garcez, Artur d’Avila; Lamb, Luis C.; Gabbay, Dov M. (2009 ). Neural-Symbolic Cognitive Reasoning (1st ed.). Berlin-Heidelberg: Springer. Bibcode:2009 nscr.book … D. doi:10.1007/ 978-3-540-73246-4. ISBN 978-3-540-73245-7. S2CID 14002173.
^ Kiczales, Gregor; Rivieres, Jim des; Bobrow, Daniel G. (1991-07-30). The Art of the Metaobject Protocol (1st ed.). Cambridge, Mass: The MIT Press. ISBN 978-0-262-61074-2.
^ Motik, Boris; Shearer, Rob; Horrocks, Ian (2009-10-28). “Hypertableau Reasoning for Description Logics”. Journal of Expert System Research. 36: 165-228. arXiv:1401.3485. doi:10.1613/ jair.2811. ISSN 1076-9757. S2CID 190609.
^ Kuipers, Benjamin (1994 ). Qualitative Reasoning: Modeling and Simulation with Incomplete Knowledge. MIT Press. ISBN 978-0-262-51540-5.
^ Russell & Norvig 2021.
^ Leo de Penning, Artur S. d’Avila Garcez, Luís C. Lamb, John-Jules Ch. Meyer: “A Neural-Symbolic Cognitive Agent for Online Learning and Reasoning.” IJCAI 2011: 1653-1658.
^ McCarthy & Hayes 1969.
^ McCarthy 1959.
^ Nilsson 1998, p. 7.
^ Olazaran 1993, pp. 411-416.
^ Olazaran 1993, pp. 415-416.
^ Marcus 2020, p. 20.
^ Garcez & Lamb 2020, p. 8.
^ a b Russell & Norvig 2021, p. 982.
^ Brooks 1991, p. 143.
^ Brooks 1991, p. 151.
^ Brooks 1991, p. 150.
^ Brooks 1991, p. 142.
References

Brooks, Rodney A. (1991 ). “Intelligence without representation”. Expert system. 47 (1 ): 139-159. doi:10.1016/ 0004-3702( 91 )90053-M. ISSN 0004-3702. S2CID 207507849. Retrieved 2022-09-13.
Clancey, William (1987 ). Knowledge-Based Tutoring: The GUIDON Program (MIT Press Series in Artificial Intelligence) (Hardcover ed.).
Crevier, Daniel (1993 ). AI: The Tumultuous Search for Expert System. New York City, NY: BasicBooks. ISBN 0-465-02997-3.
Dreyfus, Hubert L (1981 ). “From micro-worlds to understanding representation: AI at an impasse” (PDF). Mind Design. MIT Press, Cambridge, MA: 161-204.
Garcez, Artur S. d’Avila; Broda, Krysia; Gabbay, Dov M.; Gabbay, Augustus de Morgan Professor of Logic Dov M. (2002 ). Neural-Symbolic Learning Systems: Foundations and Applications. Springer Science & Business Media. ISBN 978-1-85233-512-0.
Garcez, Artur; Besold, Tarek; De Raedt, Luc; Földiák, Peter; Hitzler, Pascal; Icard, Thomas; Kühnberger, Kai-Uwe; Lamb, Luís; Miikkulainen, Risto; Silver, Daniel (2015 ). Neural-Symbolic Learning and Reasoning: Contributions and Challenges. AAI Spring Symposium – Knowledge Representation and Reasoning: Integrating Symbolic and Neural Approaches. Stanford, CA: AAAI Press. doi:10.13140/ 2.1.1779.4243.
Garcez, Artur d’Avila; Gori, Marco; Lamb, Luis C.; Serafini, Luciano; Spranger, Michael; Tran, Son N. (2019 ), Neural-Symbolic Computing: A Reliable Methodology for Principled Integration of Artificial Intelligence and Reasoning, arXiv:1905.06088.
Garcez, Artur d’Avila; Lamb, Luis C. (2020 ), Neurosymbolic AI: The 3rd Wave, arXiv:2012.05876.
Haugeland, John (1985 ), Expert System: The Very Idea, Cambridge, Mass: MIT Press, ISBN 0-262-08153-9.
Hayes-Roth, Frederick; Murray, William; Adelman, Leonard (2015 ). “Expert systems”. AccessScience. doi:10.1036/ 1097-8542.248550.
Honavar, Vasant; Uhr, Leonard (1994 ). Symbolic Expert System, Connectionist Networks & Beyond (Technical report). Iowa State University Digital Repository, Computer Technology Technical Reports. 76. p. 6.
Honavar, Vasant (1995 ). Symbolic Expert System and Numeric Artificial Neural Networks: Towards a Resolution of the Dichotomy. The Springer International Series In Engineering and Computer Science. Springer US. pp. 351-388. doi:10.1007/ 978-0-585-29599-2_11.
Howe, J. (November 1994). “Expert System at Edinburgh University: a Viewpoint”. Archived from the initial on 15 May 2007. Retrieved 30 August 2007.
Kautz, Henry (2020-02-11). The Third AI Summer, Henry Kautz, AAAI 2020 Robert S. Engelmore Memorial Award Lecture. Retrieved 2022-07-06.
Kautz, Henry (2022 ). “The Third AI Summer: AAAI Robert S. Engelmore Memorial Lecture”. AI Magazine. 43 (1 ): 93-104. doi:10.1609/ aimag.v43i1.19122. ISSN 2371-9621. S2CID 248213051. Retrieved 2022-07-12.
Kodratoff, Yves; Michalski, Ryszard, eds. (1990 ). Machine Learning: an Expert System Approach. Vol. III. San Mateo, Calif.: Morgan Kaufman. ISBN 0-934613-09-5. OCLC 893488404.
Kolata, G. (1982 ). “How can computers get good sense?”. Science. 217 (4566 ): 1237-1238. Bibcode:1982 Sci … 217.1237 K. doi:10.1126/ science.217.4566.1237. PMID 17837639.
Maker, Meg Houston (2006 ). “AI@50: AI Past, Present, Future”. Dartmouth College. Archived from the original on 3 January 2007. Retrieved 16 October 2008.
Marcus, Gary; Davis, Ernest (2019 ). Rebooting AI: Building Artificial Intelligence We Can Trust. New York City: Pantheon Books. ISBN 9781524748258. OCLC 1083223029.
Marcus, Gary (2020 ), The Next Decade in AI: Four Steps Towards Robust Expert system, arXiv:2002.06177.
McCarthy, John (1959 ). PROGRAMS WITH COMMON SENSE. Symposium on Mechanization of Thought Processes. NATIONAL PHYSICAL LABORATORY, TEDDINGTON, UK. p. 8.
McCarthy, John; Hayes, Patrick (1969 ). “Some Philosophical Problems From the Standpoint of Expert System”. Machine Intelligence 4. B. Meltzer, Donald Michie (eds.): 463-502.
McCorduck, Pamela (2004 ), Machines Who Think (2nd ed.), Natick, Massachusetts: A. K. Peters, ISBN 1-5688-1205-1.
Michalski, Ryszard; Carbonell, Jaime; Mitchell, Tom, eds. (1983 ). Artificial intelligence: an Artificial Intelligence Approach. Vol. I. Palo Alto, Calif.: Tioga Publishing Company. ISBN 0-935382-05-4. OCLC 9262069.
Michalski, Ryszard; Carbonell, Jaime; Mitchell, Tom, eds. (1986 ). Artificial intelligence: an Expert System Approach. Vol. II. Los Altos, Calif.: Morgan Kaufman. ISBN 0-934613-00-1.
Newell, Allen; Simon, Herbert A. (1972 ). Human Problem Solving (1st ed.). Englewood Cliffs, New Jersey: Prentice Hall. ISBN 0-13-445403-0.
Newell, Allen; Simon, H. A. (1976 ). “Computer Technology as Empirical Inquiry: Symbols and Search”. Communications of the ACM. 19 (3 ): 113-126. doi:10.1145/ 360018.360022.
Nilsson, Nils (1998 ). Artificial Intelligence: A New Synthesis. Morgan Kaufmann. ISBN 978-1-55860-467-4. Archived from the original on 26 July 2020. Retrieved 18 November 2019.
Olazaran, Mikel (1993-01-01), “A Sociological History of the Neural Network Controversy”, in Yovits, Marshall C. (ed.), Advances in Computers Volume 37, vol. 37, Elsevier, pp. 335-425, doi:10.1016/ S0065-2458( 08 )60408-8, ISBN 9780120121373, retrieved 2023-10-31.
Pearl, J. (1988 ). Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. San Mateo, California: Morgan Kaufmann. ISBN 978-1-55860-479-7. OCLC 249625842.
Russell, Stuart J.; Norvig, Peter (2021 ). Artificial Intelligence: A Modern Approach (4th ed.). Hoboken: Pearson. ISBN 978-0-13-461099-3. LCCN 20190474.
Rossi, Francesca (2022-07-06). “AAAI2022: Thinking Fast and Slow in AI (AAAI 2022 Invited Talk)”. Retrieved 2022-07-06.
Selman, Bart (2022-07-06). “AAAI2022: Presidential Address: The State of AI“. Retrieved 2022-07-06.
Serafini, Luciano; Garcez, Artur d’Avila (2016-07-07), Logic Tensor Networks: Deep Learning and Logical Reasoning from Data and Knowledge, arXiv:1606.04422.
Spiegelhalter, David J.; Dawid, A. Philip; Lauritzen, Steffen; Cowell, Robert G. (1993 ). “Bayesian analysis in specialist systems”. Statistical Science. 8 (3 ).
Turing, A. M. (1950 ). “I.-Computing Machinery and Intelligence”. Mind. LIX (236 ): 433-460. doi:10.1093/ mind/LIX.236.433. ISSN 0026-4423. Retrieved 2022-09-14.
Valiant, Leslie G (2008 ). “Knowledge Infusion: In Pursuit of Robustness in Expert System”. In Hariharan, R.; Mukund, M.; Vinay, V. (eds.). Foundations of Software Technology and Theoretical Computer Science (Bangalore). pp. 415-422.
Xifan Yao; Jiajun Zhou; Jiangming Zhang; Claudio R. Boer (2017 ). From Intelligent Manufacturing to Smart Manufacturing for Industry 4.0 Driven by Next Generation Expert System and Further On.