Symbolic Expert System

In expert system, symbolic artificial intelligence (also called classical expert system or logic-based expert system) [1] [2] is the term for the collection of all methods in expert system research study that are based upon high-level symbolic (human-readable) representations of problems, reasoning and search. [3] Symbolic AI utilized tools such as reasoning programs, production guidelines, semantic webs and frames, and it developed 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 resulted in critical ideas in search, symbolic programs 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 till the mid-1990s. [4] Researchers in the 1960s and the 1970s were encouraged that symbolic approaches would ultimately succeed in developing a machine with synthetic general intelligence and considered this the supreme goal of their field. [citation required] An early boom, with early successes such as the Logic Theorist and Samuel’s Checkers Playing Program, resulted in impractical expectations and pledges 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 pledge of catching business know-how, and a passionate corporate accept. [7] [8] That boom, and some early successes, e.g., with XCON at DEC, was followed once again by later frustration. [8] Problems with troubles in understanding acquisition, keeping large knowledge bases, and brittleness in handling out-of-domain problems developed. Another, 2nd, AI Winter (1988-2011) followed. [9] Subsequently, AI scientists concentrated on resolving underlying issues in managing unpredictability and in understanding acquisition. [10] Uncertainty was attended to with official approaches such as covert Markov designs, Bayesian reasoning, and analytical relational learning. [11] [12] Symbolic machine finding out addressed the knowledge acquisition issue with contributions including Version Space, Valiant’s PAC learning, Quinlan’s ID3 decision-tree knowing, case-based knowing, and inductive logic programs to discover relations. [13]

Neural networks, a subsymbolic technique, had been pursued from early days and reemerged strongly in 2012. Early examples are Rosenblatt’s perceptron knowing 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 considered as successful up until about 2012: “Until Big Data became prevalent, the basic 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 approaches. … A revolution came in 2012, when a number of individuals, consisting of a team of researchers dealing with Hinton, exercised a way to use the power of GPUs to enormously increase the power of neural networks.” [16] Over the next several years, deep knowing had amazing success in handling vision, speech acknowledgment, speech synthesis, image generation, and machine translation. However, because 2020, as intrinsic difficulties with predisposition, explanation, coherence, and effectiveness ended up being more evident with deep knowing techniques; an increasing variety of AI scientists have actually required combining the very best of both the symbolic and neural network techniques [17] [18] and attending to areas that both approaches have problem with, such as common-sense thinking. [16]

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

The first AI summer: unreasonable exuberance, 1948-1966

Success at early attempts in AI happened in three main locations: synthetic neural networks, knowledge representation, and heuristic search, contributing to high expectations. This area sums up Kautz’s reprise of early AI history.

Approaches motivated by human or animal cognition or habits

Cybernetic methods attempted to replicate the feedback loops in between animals and their environments. A robotic turtle, with sensing units, motors for driving and guiding, and 7 vacuum tubes for control, based upon a preprogrammed neural net, was developed as early as 1948. This work can be viewed as an early precursor to later work in neural networks, support knowing, and situated robotics. [20]

An important 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 primary 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 resolved issues represented with official operators by means of state-space search using means-ends analysis. [21]

During the 1960s, symbolic techniques accomplished great success at simulating intelligent habits in structured environments such as game-playing, symbolic mathematics, and theorem-proving. AI research study was concentrated in 4 institutions in the 1960s: Carnegie Mellon University, Stanford, MIT and (later on) University of Edinburgh. Each one developed its own design of research study. Earlier techniques based upon cybernetics or artificial neural networks were deserted or pressed into the background.

Herbert Simon and Allen Newell studied human problem-solving skills and tried to formalize them, and their work laid the foundations of the field of expert system, along with cognitive science, operations research study and management science. Their research team used the outcomes of psychological experiments to develop programs that simulated the techniques that people used to solve problems. [22] [23] This tradition, centered at Carnegie Mellon University would eventually culminate in the advancement of the Soar architecture in the middle 1980s. [24] [25]

Heuristic search

In addition to the highly specialized domain-specific sort of understanding that we will see later utilized in specialist systems, early symbolic AI scientists discovered another more basic application of knowledge. These were called heuristics, rules of thumb that guide a search in promising directions: “How can non-enumerative search be practical when the underlying problem is exponentially hard? The technique promoted by Simon and Newell is to utilize heuristics: quick algorithms that might fail on some inputs or output suboptimal solutions.” [26] Another crucial advance was to discover a method to apply these heuristics that ensures an option will be discovered, if there is one, not holding up against the periodic fallibility of heuristics: “The A * algorithm provided a general frame for complete and ideal heuristically guided search. A * is utilized as a subroutine within practically every AI algorithm today but is still no magic bullet; its guarantee of efficiency is purchased the expense of worst-case exponential time. [26]

Early work on knowledge representation and reasoning

Early work covered both applications of official reasoning highlighting first-order logic, in addition to efforts to deal with sensible reasoning in a less official way.

Modeling official thinking with logic: the “neats”

Unlike Simon and Newell, John McCarthy felt that devices did not need to imitate the exact mechanisms of human thought, but could rather search for the essence of abstract thinking and analytical with reasoning, [27] despite whether individuals utilized the exact same algorithms. [a] His lab at Stanford (SAIL) concentrated on utilizing formal logic to solve a wide array of issues, consisting of knowledge representation, preparation and learning. [31] Logic was likewise the focus of the work at the University of Edinburgh and in other places in Europe which resulted in the development of the programs language Prolog and the science of reasoning programs. [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] found that fixing difficult issues in vision and natural language processing required advertisement hoc solutions-they argued that no basic and general concept (like logic) would capture all the elements of smart habits. Roger Schank explained their “anti-logic” approaches as “scruffy” (as opposed to the “cool” paradigms at CMU and Stanford). [36] [37] Commonsense understanding bases (such as Doug Lenat’s Cyc) are an example of “scruffy” AI, since they must be developed by hand, one complicated idea at a time. [38] [39] [40]

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

The first AI winter season was a shock:

During the very first AI summertime, lots of people believed that device intelligence could be accomplished in simply a couple of years. The Defense Advance Research Projects Agency (DARPA) released programs to support AI research to utilize AI to solve problems of national security; in specific, to automate the translation of Russian to English for intelligence operations and to produce self-governing tanks for the battlefield. Researchers had actually started to recognize that accomplishing AI was going to be much more difficult than was supposed a years previously, however a mix of hubris and disingenuousness led many university and think-tank scientists to accept funding with pledges of deliverables that they should have known they could not satisfy. By the mid-1960s neither useful natural language translation systems nor self-governing tanks had actually been created, and a significant backlash embeded in. New DARPA leadership canceled existing AI funding programs.

Outside of the United States, the most fertile ground for AI research was the UK. The AI winter in the United Kingdom was stimulated on not so much by disappointed military leaders as by competing academics who saw AI scientists as charlatans and a drain on research study funding. A professor of used mathematics, Sir James Lighthill, was commissioned by Parliament to evaluate the state of AI research study in the country. The report stated that all of the issues being worked on in AI would be better managed by scientists from other disciplines-such as used mathematics. The report likewise declared that AI successes on toy issues could never scale to real-world applications due to combinatorial explosion. [41]

The 2nd AI summertime: knowledge is power, 1978-1987

Knowledge-based systems

As restrictions with weak, domain-independent techniques became more and more apparent, [42] researchers from all three customs began to build knowledge into AI applications. [43] [7] The knowledge transformation was driven by the realization that knowledge underlies high-performance, domain-specific AI applications.

Edward Feigenbaum said:

– “In the knowledge lies the power.” [44]
to describe that high efficiency in a specific domain needs both general 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 an intricate job well, it needs to know a great offer about the world in which it runs.
( 2) A possible extension of that principle, called the Breadth Hypothesis: there are two additional capabilities essential for smart behavior in unanticipated scenarios: drawing on progressively basic knowledge, and analogizing to specific but remote understanding. [45]

Success with professional systems

This “understanding transformation” led to the development and implementation of professional systems (presented by Edward Feigenbaum), the first commercially successful form of AI software application. [46] [47] [48]

Key specialist systems were:

DENDRAL, which discovered the structure of natural particles from their chemical formula and mass spectrometer readings.
MYCIN, which detected bacteremia – and suggested further lab tests, when required – by translating laboratory results, patient history, and medical professional observations. “With about 450 rules, MYCIN had the ability to carry out as well as some experts, and significantly better than junior doctors.” [49] INTERNIST and CADUCEUS which tackled internal medicine medical diagnosis. Internist tried to capture the proficiency of the chairman of internal medicine at the University of Pittsburgh School of Medicine while CADUCEUS could ultimately identify approximately 1000 different illness.
– GUIDON, which demonstrated how an understanding base built for specialist issue resolving might be repurposed for mentor. [50] XCON, to configure VAX computers, a then tiresome procedure that might use up to 90 days. XCON minimized the time to about 90 minutes. [9]
DENDRAL is thought about the first expert system that relied on knowledge-intensive analytical. It is explained below, by Ed Feigenbaum, from a Communications of the ACM interview, Interview with Ed Feigenbaum:

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

We did not have a grandiose vision. We worked bottom up. Our chemist was Carl Djerassi, developer of the chemical behind the birth control pill, and also among the world’s most respected mass spectrometrists. Carl and his postdocs were first-rate experts in mass spectrometry. We began to include to their understanding, creating understanding of engineering as we went along. These experiments amounted to titrating DENDRAL more and more knowledge. The more you did that, the smarter the program became. We had very great results.

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

The other expert systems mentioned above came after DENDRAL. MYCIN exemplifies the timeless expert system architecture of a knowledge-base of guidelines coupled to a symbolic thinking system, consisting of making use of certainty elements to deal with uncertainty. GUIDON shows how an explicit knowledge base can be repurposed for a 2nd application, tutoring, and is an example of an intelligent tutoring system, a particular kind of knowledge-based application. Clancey showed that it was not sufficient just to use MYCIN’s guidelines for guideline, however that he also required to include rules for dialogue management and trainee modeling. [50] XCON is substantial due to the fact that of the millions of dollars it conserved DEC, which activated the professional system boom where most all significant corporations in the US had skilled systems groups, to capture corporate expertise, protect it, and automate it:

By 1988, DEC’s AI group had 40 specialist systems released, with more en route. DuPont had 100 in usage and 500 in advancement. Nearly every significant U.S. corporation had its own Al group and was either using or investigating specialist systems. [49]

Chess specialist knowledge was encoded in Deep Blue. In 1996, this enabled IBM’s Deep Blue, with the help of symbolic AI, to win in a game of chess against the world champion at that time, Garry Kasparov. [52]

Architecture of knowledge-based and skilled systems

A key component of the system architecture for all professional systems is the understanding base, which stores realities and rules for analytical. [53] The easiest method for an expert system understanding base is just a collection or network of production rules. Production rules link signs in a relationship comparable to an If-Then declaration. The specialist system processes the rules to make reductions and to determine what additional info it needs, i.e. what concerns to ask, using 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 proof to conclusions – or backwards chaining – from objectives to required data and prerequisites – manner. Advanced knowledge-based systems, such as Soar can also perform meta-level reasoning, that is reasoning about their own thinking in terms of deciding how to resolve issues and monitoring the success of problem-solving techniques.

Blackboard systems are a 2nd sort of knowledge-based or skilled system architecture. They model a community of experts incrementally contributing, where they can, to solve a problem. The problem is represented in multiple levels of abstraction or alternate views. The specialists (understanding sources) offer their services whenever they acknowledge they can contribute. Potential problem-solving actions are represented on an agenda that is upgraded as the problem situation modifications. A controller chooses how useful each contribution is, and who must make the next analytical action. One example, the BB1 blackboard architecture [54] was initially motivated by research studies of how people prepare to carry out numerous tasks in a journey. [55] A development of BB1 was to apply the same blackboard model to solving its control issue, i.e., its controller performed meta-level reasoning with understanding sources that kept an eye on how well a strategy or the problem-solving was proceeding and might switch from one technique to another as conditions – such as objectives or times – changed. BB1 has actually been applied in multiple domains: building website preparation, smart tutoring systems, and real-time client tracking.

The 2nd AI winter season, 1988-1993

At the height of the AI boom, business such as Symbolics, LMI, and Texas Instruments were offering LISP devices specifically targeted to speed up the development of AI applications and research study. In addition, numerous expert system companies, such as Teknowledge and Inference Corporation, were offering skilled system shells, training, and seeking advice from to corporations.

Unfortunately, the AI boom did not last and Kautz best explains the 2nd AI winter season that followed:

Many factors can be offered for the arrival of the 2nd AI winter. The hardware companies stopped working when far more economical basic Unix workstations from Sun together with great compilers for LISP and Prolog came onto the market. Many business implementations of expert systems were discontinued when they proved too costly to keep. Medical specialist systems never caught on for a number of reasons: the trouble in keeping them approximately date; the challenge for medical professionals to learn how to use a bewildering range of various expert systems for different medical conditions; and perhaps most crucially, the hesitation of medical professionals to trust a computer-made diagnosis over their gut impulse, even for specific domains where the specialist systems could surpass a typical doctor. Venture capital cash deserted AI almost overnight. The world AI conference IJCAI hosted a huge and extravagant trade show and countless nonacademic participants in 1987 in Vancouver; the main AI conference the following year, AAAI 1988 in St. Paul, was a little and strictly academic affair. [9]

Adding in more rigorous structures, 1993-2011

Uncertain thinking

Both analytical methods and extensions to logic were tried.

One statistical approach, concealed Markov designs, had actually currently been popularized in the 1980s for speech acknowledgment work. [11] Subsequently, in 1988, Judea Pearl promoted the usage of Bayesian Networks as a noise however effective way of managing unsure reasoning with his publication of the book Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. [56] and Bayesian approaches were used successfully in expert systems. [57] Even later, in the 1990s, statistical relational knowing, a method that combines possibility with rational formulas, allowed likelihood to be combined with first-order reasoning, e.g., with either Markov Logic Networks or Probabilistic Soft Logic.

Other, non-probabilistic extensions to first-order reasoning to support were also tried. For instance, non-monotonic reasoning might be utilized with reality maintenance systems. A reality maintenance system tracked assumptions and justifications for all inferences. It permitted reasonings to be withdrawn when presumptions were learnt to be incorrect or a contradiction was obtained. Explanations might be offered an inference by discussing which rules were applied to create it and after that continuing through underlying reasonings and rules all the method back to root assumptions. [58] Lofti Zadeh had actually introduced a various type of extension to manage the representation of vagueness. For instance, in deciding how “heavy” or “high” a guy is, there is regularly no clear “yes” or “no” answer, and a predicate for heavy or high would instead return values in between 0 and 1. Those values represented to what degree the predicates were real. His fuzzy reasoning further supplied a way for propagating mixes of these worths through logical solutions. [59]

Machine knowing

Symbolic machine learning methods were investigated to resolve the understanding acquisition traffic jam. One of the earliest is Meta-DENDRAL. Meta-DENDRAL used a generate-and-test technique to generate plausible guideline hypotheses to test versus spectra. Domain and task knowledge minimized the number of candidates tested to a manageable size. Feigenbaum explained Meta-DENDRAL as

… the conclusion of my dream of the early to mid-1960s involving theory development. The conception was that you had a problem solver like DENDRAL that took some inputs and produced an output. In doing so, it utilized layers of understanding to steer and prune the search. That understanding got in there due to the fact that we spoke with individuals. But how did the individuals get the knowledge? By taking a look at thousands of spectra. So we desired a program that would look at thousands of spectra and presume the understanding of mass spectrometry that DENDRAL might use to fix private hypothesis formation problems. We did it. We were even able to release brand-new understanding of mass spectrometry in the Journal of the American Chemical Society, offering credit only in a footnote that a program, Meta-DENDRAL, actually did it. We were able to do something that had actually been a dream: to have a computer system program come up with a new and publishable piece of science. [51]

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

Advances were made in comprehending device learning theory, too. Tom Mitchell presented version area learning which explains learning as a search through a space of hypotheses, with upper, more basic, and lower, more particular, limits incorporating all feasible hypotheses consistent with the examples seen up until now. [62] More formally, Valiant presented Probably Approximately Correct Learning (PAC Learning), a framework for the mathematical analysis of artificial intelligence. [63]

Symbolic device learning included more than discovering by example. E.g., John Anderson offered a cognitive design of human learning where skill practice leads to a collection of rules from a declarative format to a procedural format with his ACT-R cognitive architecture. For instance, a student might find out to apply “Supplementary angles are 2 angles whose procedures sum 180 degrees” as several various procedural guidelines. E.g., one rule might state that if X and Y are supplemental and you know X, then Y will be 180 – X. He called his approach “understanding compilation”. ACT-R has actually been used successfully to design aspects of human cognition, such as finding out and retention. ACT-R is also utilized in smart tutoring systems, called cognitive tutors, to effectively teach geometry, computer programming, and algebra to school children. [64]

Inductive reasoning programming was another method to learning that allowed logic programs to be synthesized from input-output examples. E.g., Ehud Shapiro’s MIS (Model Inference System) might manufacture Prolog programs from examples. [65] John R. Koza used genetic algorithms to program synthesis to create genetic programs, which he utilized to manufacture LISP programs. Finally, Zohar Manna and Richard Waldinger supplied a more basic technique to program synthesis that synthesizes a functional program in the course of proving its specs to be right. [66]

As an option to reasoning, Roger Schank introduced case-based reasoning (CBR). The CBR method outlined in his book, Dynamic Memory, [67] focuses first on remembering crucial analytical cases for future usage and generalizing them where appropriate. When faced with a new issue, CBR recovers the most similar previous case and adjusts it to the specifics of the existing issue. [68] Another option to reasoning, hereditary algorithms and hereditary shows are based upon an evolutionary design of knowing, where sets of rules are encoded into populations, the rules govern the behavior of individuals, and choice of the fittest prunes out sets of inappropriate rules over numerous generations. [69]

Symbolic artificial intelligence was applied to discovering principles, rules, heuristics, and problem-solving. Approaches, besides those above, include:

1. Learning from guideline or advice-i.e., taking human direction, posed as guidance, and determining how to operationalize it in specific situations. For instance, in a game of Hearts, finding out precisely how to play a hand to “prevent taking points.” [70] 2. Learning from exemplars-improving performance by accepting subject-matter specialist (SME) feedback throughout training. When analytical stops working, querying the professional to either find out a brand-new exemplar for analytical or to discover a brand-new explanation as to exactly why one prototype is more appropriate than another. For instance, the program Protos learned to diagnose ringing in the ears cases by engaging with an audiologist. [71] 3. Learning by analogy-constructing problem solutions based upon similar problems seen in the past, and then modifying their solutions to fit a new scenario or domain. [72] [73] 4. Apprentice learning systems-learning unique services to issues by observing human analytical. Domain knowledge explains why unique services are correct and how the solution can be generalized. LEAP discovered how to create VLSI circuits by observing human designers. [74] 5. Learning by discovery-i.e., creating tasks to carry out experiments and then gaining from the results. Doug Lenat’s Eurisko, for instance, found out heuristics to beat human gamers at the Traveller role-playing game for 2 years in a row. [75] 6. Learning macro-operators-i.e., looking for helpful macro-operators to be discovered from sequences of basic problem-solving actions. Good macro-operators streamline problem-solving by enabling issues to be fixed at a more abstract level. [76]
Deep knowing and neuro-symbolic AI 2011-now

With the increase of deep learning, the symbolic AI approach has actually been compared to deep learning as complementary “… with parallels having been drawn sometimes by AI scientists in between Kahneman’s research study on human reasoning 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 learning and symbolic thinking, respectively.” In this view, symbolic thinking is more apt for deliberative reasoning, planning, and description while deep learning is more apt for quick pattern acknowledgment in affective applications with noisy information. [17] [18]

Neuro-symbolic AI: integrating neural and symbolic techniques

Neuro-symbolic AI efforts to integrate neural and symbolic architectures in a way that addresses strengths and weak points 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 building of rich computational cognitive models demands the mix of sound symbolic reasoning and efficient (maker) knowing models. Gary Marcus, similarly, argues that: “We can not construct rich cognitive designs in a sufficient, automatic way without the triumvirate of hybrid architecture, abundant prior knowledge, and advanced strategies for reasoning.”, [79] and in specific: “To build a robust, knowledge-driven approach to AI we should have the machinery of symbol-manipulation in our toolkit. Too much of helpful 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 reliably is the apparatus of sign manipulation. ” [80]

Henry Kautz, [19] Francesca Rossi, [81] and Bart Selman [82] have likewise argued for a synthesis. Their arguments are based upon a need to resolve the two sort of thinking talked about in Daniel Kahneman’s book, Thinking, Fast and Slow. Kahneman describes human thinking as having two components, System 1 and System 2. System 1 is quick, automated, user-friendly and unconscious. System 2 is slower, step-by-step, and specific. System 1 is the kind utilized for pattern acknowledgment while System 2 is far much better matched for planning, deduction, and deliberative thinking. In this view, deep learning best models the very first kind of believing while symbolic reasoning best models the second kind and both are required.

Garcez and Lamb explain research study in this area as being ongoing for at least the previous twenty years, [83] dating from their 2002 book on neurosymbolic learning systems. [84] A series of workshops on neuro-symbolic reasoning has 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 fairly little research community over the last 20 years and has actually yielded a number of significant outcomes. Over the last decade, neural symbolic systems have actually been shown capable of overcoming the so-called propositional fixation of neural networks, as McCarthy (1988) put it in action to Smolensky (1988 ); see also (Hinton, 1990). Neural networks were revealed capable of representing modal and temporal reasonings (d’Avila Garcez and Lamb, 2006) and fragments of first-order reasoning (Bader, Hitzler, Hölldobler, 2008; d’Avila Garcez, Lamb, Gabbay, 2009). Further, neural-symbolic systems have been used to a number of issues in the locations of bioinformatics, control engineering, software verification and adaptation, visual intelligence, ontology knowing, and computer system games. [78]

Approaches for integration are differed. Henry Kautz’s taxonomy of neuro-symbolic architectures, in addition to some examples, follows:

– Symbolic Neural symbolic-is the present method of lots of neural models in natural language processing, where words or subword tokens are both the ultimate input and output of large language designs. Examples include BERT, RoBERTa, and GPT-3.
– Symbolic [Neural] -is exhibited by AlphaGo, where symbolic strategies are used to call neural techniques. In this case the symbolic approach is Monte Carlo tree search and the neural techniques learn how to examine video game positions.
– Neural|Symbolic-uses a neural architecture to translate perceptual information as signs and relationships that are then reasoned about symbolically.
– Neural: Symbolic → Neural-relies on symbolic thinking to produce or label training information that is subsequently discovered by a deep learning design, e.g., to train a neural design for symbolic calculation by using a Macsyma-like symbolic mathematics system to develop or label examples.
– Neural _ Symbolic -uses a neural internet that is created 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] also fall under this classification.
– Neural [Symbolic] -permits a neural design to directly call a symbolic thinking engine, e.g., to carry out an action or examine a state.

Many essential research concerns remain, such as:

– What is the finest method to integrate neural and symbolic architectures? [87]- How should symbolic structures be represented within neural networks and drawn out from them?
– How should sensible understanding be discovered and reasoned about?
– How can abstract knowledge that is difficult to encode rationally be handled?

Techniques and contributions

This area offers an overview of methods and contributions in an overall context resulting in lots of other, more in-depth short articles in Wikipedia. Sections on Machine Learning and Uncertain Reasoning are covered previously in the history area.

AI programs languages

The crucial AI shows language in the US during the last symbolic AI boom duration was LISP. LISP is the second oldest programming language after FORTRAN and was created in 1958 by John McCarthy. LISP supplied the first read-eval-print loop to support rapid program development. Compiled functions could be freely combined with interpreted functions. Program tracing, stepping, and breakpoints were also offered, in addition to the capability to alter values or functions and continue from breakpoints or errors. It had the very first self-hosting compiler, meaning that the compiler itself was initially written in LISP and after that ran interpretively to compile the compiler code.

Other key developments originated by LISP that have infected other shows languages consist of:

Garbage collection
Dynamic typing
Higher-order functions
Recursion
Conditionals

Programs were themselves data structures that other programs might run on, permitting the easy definition of higher-level languages.

In contrast to the US, in Europe the key AI shows language throughout that same duration was Prolog. Prolog provided an integrated shop of realities and clauses that could be queried by a read-eval-print loop. The shop might function as an understanding base and the stipulations could serve as guidelines or a limited type of logic. As a subset of first-order reasoning Prolog was based upon Horn stipulations with a closed-world assumption-any realities not understood were considered false-and a special name assumption for primitive terms-e.g., the identifier barack_obama was considered to describe precisely one object. Backtracking and marriage are integrated to Prolog.

Alain Colmerauer and Philippe Roussel are credited as the developers of Prolog. Prolog is a form of reasoning shows, which was created by Robert Kowalski. Its history was also influenced by Carl Hewitt’s PLANNER, an assertional database with pattern-directed invocation of approaches. For more detail see the area on the origins of Prolog in the PLANNER post.

Prolog is also a sort of declarative programs. The reasoning provisions that explain programs are straight interpreted to run the programs specified. No explicit series of actions is needed, as is the case with important programming languages.

Japan championed Prolog for its Fifth Generation Project, meaning to develop special hardware for high efficiency. Similarly, LISP devices were built to run LISP, but as the second AI boom turned to bust these business might not take on new workstations that might now run LISP or Prolog natively at comparable speeds. See the history section for more information.

Smalltalk was another influential AI programs language. For instance, it presented metaclasses and, together 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 enables several inheritance, in addition to incremental extensions to both classes and metaclasses, hence supplying a run-time meta-object procedure. [88]

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

Search

Search emerges in many kinds of issue resolving, including preparation, restraint fulfillment, and playing video 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 stipulation knowing, 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 knowledge and then reason with those representations have been investigated. Below is a quick overview of techniques to understanding representation and automated thinking.

Knowledge representation

Semantic networks, conceptual charts, frames, and reasoning are all methods to modeling knowledge such as domain knowledge, problem-solving knowledge, and the semantic significance of language. Ontologies model crucial 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 also be viewed as an ontology. YAGO integrates WordNet as part of its ontology, to align facts extracted from Wikipedia with WordNet synsets. The Disease Ontology is an example of a medical ontology presently being used.

Description logic is a reasoning for automated category of ontologies and for spotting irregular category information. OWL is a language used to represent ontologies with description reasoning. Protégé is an ontology editor that can read in OWL ontologies and then examine consistency with deductive classifiers such as such as HermiT. [89]

First-order logic is more general than description reasoning. The automated theorem provers talked about listed below can prove theorems in first-order logic. Horn stipulation reasoning is more limited than first-order logic and is used in reasoning shows languages such as Prolog. Extensions to first-order logic include temporal logic, to manage time; epistemic logic, to factor about representative understanding; modal reasoning, to manage possibility and requirement; and probabilistic reasonings to manage logic and likelihood together.

Automatic theorem showing

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

Prover9.
ACL2.
Vampire.

Prover9 can be used in combination with the Mace4 design checker. ACL2 is a theorem prover that can handle evidence 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 improve reusability throughout domains by separating procedural code and domain understanding. A separate reasoning engine procedures guidelines and adds, deletes, or modifies an understanding store.

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

A more versatile type of analytical happens when thinking about what to do next happens, rather than simply selecting one of the offered actions. This type of meta-level reasoning is used in Soar and in the BB1 blackboard architecture.

Cognitive architectures such as ACT-R may have extra abilities, such as the ability to assemble regularly utilized understanding into higher-level pieces.

Commonsense reasoning

Marvin Minsky initially proposed frames as a method of analyzing common visual scenarios, such as a workplace, and Roger Schank extended this idea to scripts for common regimens, such as dining out. Cyc has attempted to capture helpful common-sense knowledge and has “micro-theories” to deal with particular type of domain-specific reasoning.

Qualitative simulation, such as Benjamin Kuipers’s QSIM, [90] estimates human thinking about naive physics, such as what takes place when we warm a liquid in a pot on the range. We anticipate it to heat and possibly boil over, even though we might not understand its temperature level, its boiling point, or other details, such as air pressure.

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

Constraints and constraint-based reasoning

Constraint solvers carry out a more limited kind of inference than first-order logic. They can simplify sets of spatiotemporal restraints, such as those for RCC or Temporal Algebra, in addition to resolving other kinds of puzzle issues, such as Wordle, Sudoku, cryptarithmetic problems, and so on. Constraint reasoning programming can be utilized to resolve scheduling issues, for instance with constraint managing guidelines (CHR).

Automated planning

The General Problem Solver (GPS) cast preparation as analytical utilized means-ends analysis to develop strategies. STRIPS took a various technique, viewing planning as theorem proving. Graphplan takes a least-commitment technique to preparation, rather than sequentially selecting actions from an initial state, working forwards, or a goal state if working backwards. Satplan is an approach to planning where a planning issue is decreased to a Boolean satisfiability problem.

Natural language processing

Natural language processing concentrates on treating language as information to perform jobs such as determining topics without always understanding the designated meaning. Natural language understanding, in contrast, constructs a significance representation and utilizes that for further processing, such as answering concerns.

Parsing, tokenizing, spelling correction, part-of-speech tagging, noun and verb phrase chunking are all aspects of natural language processing long dealt with by symbolic AI, but considering that improved by deep learning methods. In symbolic AI, discourse representation theory and first-order logic have been utilized to represent sentence significances. Latent semantic analysis (LSA) and specific semantic analysis likewise provided vector representations of documents. In the latter case, vector parts are interpretable as principles named by Wikipedia articles.

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

Agents and multi-agent systems

Agents are autonomous systems embedded in an environment they perceive and act upon in some sense. Russell and Norvig’s standard book on synthetic intelligence is arranged to show agent architectures of increasing elegance. [91] The sophistication of representatives varies from basic reactive agents, to those with a model of the world and automated preparation capabilities, perhaps a BDI representative, i.e., one with beliefs, desires, and intentions – or alternatively a support learning model discovered in time to select actions – as much as a combination of alternative architectures, such as a neuro-symbolic architecture [87] that consists of deep learning for perception. [92]

In contrast, a multi-agent system consists of several representatives that interact among themselves with some inter-agent communication 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 amongst the representatives and to increase fault tolerance when agents are lost. Research problems consist of how agents reach agreement, distributed issue fixing, multi-agent learning, multi-agent planning, and distributed constraint optimization.

Controversies developed from at an early stage in symbolic AI, both within the field-e.g., in between logicists (the pro-logic “neats”) and non-logicists (the anti-logic “scruffies”)- and in between those who welcomed AI but turned down symbolic approaches-primarily connectionists-and those outside the field. Critiques from beyond the field were primarily from theorists, on intellectual premises, however also from funding agencies, particularly during the two AI winters.

The Frame Problem: knowledge representation challenges for first-order reasoning

Limitations were found in using basic first-order reasoning to factor about vibrant domains. Problems were found both with concerns to mentioning the prerequisites for an action to be successful and in providing axioms for what did not change after an action was performed.

McCarthy and Hayes presented the Frame Problem in 1969 in the paper, “Some Philosophical Problems from the Standpoint of Artificial Intelligence.” [93] An easy example happens in “showing that one individual could enter into conversation with another”, as an axiom asserting “if a person has a telephone he still has it after looking up a number in the telephone book” would be required for the reduction to prosper. Similar axioms would be required for other domain actions to specify what did not alter.

A comparable issue, called the Qualification Problem, takes place in trying to mention the preconditions for an action to succeed. An unlimited variety of pathological conditions can be imagined, e.g., a banana in a tailpipe might prevent a car from running correctly.

McCarthy’s method to fix the frame problem was circumscription, a sort of non-monotonic logic where deductions could be made from actions that require just specify what would change while not needing to clearly define everything that would not alter. Other non-monotonic reasonings offered fact maintenance systems that revised beliefs resulting in contradictions.

Other methods of handling more open-ended domains consisted of probabilistic reasoning systems and device learning to learn new concepts and rules. McCarthy’s Advice Taker can be considered as an inspiration here, as it could integrate brand-new understanding supplied by a human in the form of assertions or guidelines. For example, experimental symbolic machine finding out systems checked out the capability to take top-level natural language suggestions and to interpret it into domain-specific actionable guidelines.

Similar to the problems in handling vibrant domains, common-sense reasoning is likewise tough to record in formal reasoning. Examples of common-sense reasoning consist of implicit reasoning about how individuals believe or general understanding of daily occasions, objects, and living animals. This kind of knowledge is taken for given and not considered as noteworthy. Common-sense reasoning is an open location of research and challenging both for symbolic systems (e.g., Cyc has attempted to capture essential parts of this understanding over more than a years) and neural systems (e.g., self-driving cars and trucks that do not know not to drive into cones or not to strike pedestrians strolling a bicycle).

McCarthy viewed his Advice Taker as having common-sense, however his meaning of common-sense was various than the one above. [94] He specified a program as having typical sense “if it instantly deduces for itself a sufficiently wide class of instant effects of anything it is informed and what it already understands. “

Connectionist AI: philosophical obstacles and sociological conflicts

Connectionist approaches include earlier deal with 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 knowing.

Three philosophical positions [96] have actually been described among connectionists:

1. Implementationism-where connectionist architectures implement the abilities for symbolic processing,
2. Radical connectionism-where symbolic processing is rejected totally, and connectionist architectures underlie intelligence and are totally enough to discuss it,
3. Moderate connectionism-where symbolic processing and connectionist architectures are considered 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 deem basically compatible with current research in neuro-symbolic hybrids:

The 3rd and last position I would like to take a look at here is what I call the moderate connectionist view, a more diverse view of the present debate in between connectionism and symbolic AI. Among the researchers who has elaborated this position most explicitly is Andy Clark, a theorist from the School of Cognitive and Computing Sciences of the University of Sussex (Brighton, England). Clark safeguarded hybrid (partly symbolic, partially connectionist) systems. He declared that (at least) two type of theories are needed in order to study and model cognition. On the one hand, for some information-processing tasks (such as pattern recognition) connectionism has advantages over symbolic models. But on the other hand, for other cognitive procedures (such as serial, deductive reasoning, and generative sign manipulation processes) the symbolic paradigm provides adequate designs, and not just “approximations” (contrary to what extreme connectionists would declare). [97]

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

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

And yet, for the a lot of part, that’s how most current AI earnings. Hinton and numerous others have tried tough to banish signs completely. The deep knowing hope-seemingly grounded not a lot in science, but in a sort of historical grudge-is that intelligent habits will emerge purely from the confluence of huge data and deep learning. Where classical computers and software application fix tasks by defining sets of symbol-manipulating guidelines dedicated to specific tasks, such as modifying a line in a word processor or performing an estimation in a spreadsheet, neural networks usually attempt to solve tasks by statistical approximation and finding out from examples.

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

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

…

Ever since, his anti-symbolic campaign has just increased in strength. In 2016, Yann LeCun, Bengio, and Hinton composed a manifesto for deep knowing in among science’s crucial journals, Nature. It closed with a direct attack on sign manipulation, calling not for reconciliation however for outright replacement. Later, Hinton informed a gathering of European Union leaders that investing any more money in symbol-manipulating techniques was “a substantial error,” comparing it to purchasing internal combustion engines in the era of electric automobiles. [98]

Part of these conflicts may be due to uncertain terms:

Turing award winner Judea Pearl provides a critique of artificial intelligence which, unfortunately, conflates the terms device learning and deep learning. Similarly, when Geoffrey Hinton describes symbolic AI, the connotation of the term tends to be that of expert systems dispossessed of any capability to find out. Using the terms needs information. Artificial intelligence is not restricted to association rule mining, c.f. the body of work on symbolic ML and relational learning (the differences to deep learning being the option of representation, localist rational instead of dispersed, and the non-use of gradient-based learning algorithms). Equally, symbolic AI is not practically production rules composed by hand. A proper definition of AI concerns understanding representation and reasoning, self-governing multi-agent systems, planning and argumentation, in addition to knowing. [99]

Situated robotics: the world as a design

Another review of symbolic AI is the embodied cognition approach:

The embodied cognition method claims that it makes no sense to consider the brain individually: 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 consistencies in its environment, consisting of the rest of its body. Under the embodied cognition approach, robotics, vision, and other sensors end up being central, not peripheral. [100]

Rodney Brooks developed behavior-based robotics, one method to embodied cognition. Nouvelle AI, another name for this technique, is deemed an alternative to both symbolic AI and connectionist AI. His technique turned down representations, either symbolic or distributed, as not only unnecessary, but as harmful. Instead, he developed the subsumption architecture, a layered architecture for embodied agents. Each layer achieves a various purpose and must function in the genuine world. For example, the very first robot he explains in Intelligence Without Representation, has three layers. The bottom layer interprets sonar sensors to prevent things. The middle layer causes the robotic to wander around when there are no barriers. The top layer triggers the robotic to go to more remote locations for additional expedition. Each layer can momentarily hinder or reduce a lower-level layer. He criticized AI scientists for specifying AI issues for their systems, when: “There is no tidy department between understanding (abstraction) and thinking in the genuine world.” [101] He called his robots “Creatures” and each layer was “made up of a fixed-topology network of basic finite state devices.” [102] In the Nouvelle AI technique, “First, it is critically important to check the Creatures we construct in the real life; i.e., in the very same world that we human beings populate. It is dreadful to fall into the temptation of checking them in a streamlined world first, even with the finest intentions of later moving activity to an unsimplified world.” [103] His focus on real-world screening was in contrast to “Early operate in AI concentrated on video games, geometrical issues, symbolic algebra, theorem proving, and other formal 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 been slammed by the other approaches. Symbolic AI has been slammed as disembodied, accountable to the certification problem, and bad in managing the affective issues where deep discovering excels. In turn, connectionist AI has been slammed as inadequately fit for deliberative step-by-step issue solving, including understanding, and dealing with planning. Finally, Nouvelle AI masters reactive and real-world robotics domains but has been slammed for problems in incorporating learning and knowledge.

Hybrid AIs including several of these methods are currently viewed as the course forward. [19] [81] [82] Russell and Norvig conclude that:

Overall, Dreyfus saw areas where AI did not have total responses and said that Al is therefore impossible; we now see a number of these exact same locations undergoing ongoing research study and development causing increased capability, not impossibility. [100]

Expert system.
Automated preparation and scheduling
Automated theorem proving
Belief revision
Case-based thinking
Cognitive architecture
Cognitive science
Connectionism
Constraint programming
Deep knowing
First-order reasoning
GOFAI
History of artificial intelligence
Inductive reasoning shows
Knowledge-based systems
Knowledge representation and thinking
Logic programming
Artificial intelligence
Model monitoring
Model-based reasoning
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 knowing
Symbolic mathematics
YAGO ontology
WordNet

Notes

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

^ Garnelo, Marta; Shanahan, Murray (October 2019). “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.
^ 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 knowing with symbolic expert system: representing items 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 Postal 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 limits 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 synthetic intelligence?”. IONOS Digitalguide. Retrieved 2021-12-02.
^ Hayes-Roth, Murray & Adelman 2015.
^ Hayes-Roth, Barbara (1985 ). “A chalkboard 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 Artificial Intelligence (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 Artificial Intelligence 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 Artificial Intelligence. 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 fifth 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 Artificial Intelligence 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”. Artificial Intelligence. 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 Artificial Intelligence. New York City, NY: BasicBooks. ISBN 0-465-02997-3.
Dreyfus, Hubert L (1981 ). “From micro-worlds to understanding representation: AI at a deadlock” (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: An Effective Methodology for Principled Integration of Machine Learning 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 Artificial Intelligence, 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). “Artificial Intelligence at Edinburgh University: a Perspective”. 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 ). Artificial intelligence: 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 sound judgment?”. 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 initial on 3 January 2007. Retrieved 16 October 2008.
Marcus, Gary; Davis, Ernest (2019 ). Rebooting AI: Building Expert System We Can Trust. New York City: Pantheon Books. ISBN 9781524748258. OCLC 1083223029.
Marcus, Gary (2020 ), The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence, arXiv:2002.06177.
McCarthy, John (1959 ). PROGRAMS WITH SOUND JUDGMENT. 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 (second ed.), Natick, Massachusetts: A. K. Peters, ISBN 1-5688-1205-1.
Michalski, Ryszard; Carbonell, Jaime; Mitchell, Tom, eds. (1983 ). Machine Learning: an Expert System 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 Artificial Intelligence 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 ). Expert system: A New Synthesis. Morgan Kaufmann. ISBN 978-1-55860-467-4. Archived from the initial on 26 July 2020. Retrieved 18 November 2019.
Olazaran, Mikel (1993-01-01), “A 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, obtained 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 (fourth 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 professional 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 Artificial Intelligence”. 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.