Symbolic Expert System

In expert system, symbolic expert system (also referred to as classical expert system or logic-based expert system) [1] [2] is the term for the collection of all techniques in expert system research study that are based upon high-level symbolic (human-readable) representations of problems, logic and search. [3] Symbolic AI used tools such as reasoning shows, production rules, semantic nets 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 caused seminal 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 from the mid-1950s until the mid-1990s. [4] Researchers in the 1960s and the 1970s were persuaded that symbolic approaches would eventually prosper in creating a maker with artificial basic intelligence and considered this the supreme objective of their field. [citation needed] An early boom, with early successes such as the Logic Theorist and Samuel’s Checkers Playing Program, caused impractical expectations and promises and was followed by the first AI Winter as funding dried up. [5] [6] A second boom (1969-1986) happened with the increase of professional systems, their guarantee of catching corporate know-how, and a passionate corporate welcome. [7] [8] That boom, and some early successes, e.g., with XCON at DEC, was followed again by later dissatisfaction. [8] Problems with problems in knowledge acquisition, preserving big understanding bases, and brittleness in managing out-of-domain issues emerged. Another, second, AI Winter (1988-2011) followed. [9] Subsequently, AI scientists focused on resolving hidden problems in managing unpredictability and in knowledge acquisition. [10] Uncertainty was attended to with formal methods such as concealed Markov designs, Bayesian thinking, and statistical relational learning. [11] [12] Symbolic device discovering dealt with the knowledge acquisition problem with contributions including Version Space, Valiant’s PAC knowing, Quinlan’s ID3 decision-tree learning, case-based learning, and inductive reasoning programs to find out relations. [13]

Neural networks, a subsymbolic technique, had actually been pursued from early days and reemerged highly in 2012. Early examples are Rosenblatt’s perceptron knowing work, the backpropagation work of Rumelhart, Hinton and Williams, [14] and work in convolutional neural networks by LeCun et al. in 1989. [15] However, neural networks were not deemed effective until about 2012: “Until Big Data became prevalent, the general agreement in the Al neighborhood was that the so-called neural-network method was helpless. Systems just didn’t work that well, compared to other techniques. … A transformation came in 2012, when a variety of individuals, including a group of scientists working with Hinton, exercised a method to use the power of GPUs to immensely increase the power of neural networks.” [16] Over the next numerous years, deep knowing had spectacular success in dealing with vision, speech recognition, speech synthesis, image generation, and maker translation. However, given that 2020, as intrinsic difficulties with bias, description, coherence, and toughness ended up being more obvious with deep knowing techniques; an increasing variety of AI scientists have called for combining the best of both the symbolic and neural network techniques [17] [18] and attending to areas that both methods have trouble with, such as common-sense reasoning. [16]

A brief history of symbolic AI to the present 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 article on the History of AI, with dates and titles varying slightly for increased clearness.

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 sums up Kautz’s reprise of early AI history.

Approaches influenced by human or animal cognition or behavior

Cybernetic techniques tried to duplicate the feedback loops in between animals and their environments. A robotic turtle, with sensors, motors for driving and guiding, and 7 vacuum tubes for control, based upon a preprogrammed neural web, was built as early as 1948. This work can be seen as an early precursor to later operate in neural networks, support knowing, and situated 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 was able to show 38 primary theorems from Whitehead and Russell’s Principia Mathematica. Newell, Simon, and Shaw later generalized this work to produce a domain-independent problem solver, GPS (General Problem Solver). GPS fixed issues represented with formal operators by means of state-space search utilizing means-ends analysis. [21]

During the 1960s, symbolic techniques accomplished fantastic success at simulating smart habits in structured environments such as game-playing, symbolic mathematics, and theorem-proving. AI research was concentrated in 4 institutions in the 1960s: Carnegie Mellon University, Stanford, MIT and (later) 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 analytical abilities and tried to formalize them, and their work laid the foundations of the field of expert system, as well as cognitive science, operations research study and . Their research team utilized the results of mental experiments to establish programs that simulated the methods that people used to resolve problems. [22] [23] This custom, focused at Carnegie Mellon University would eventually culminate in the development of the Soar architecture in the center 1980s. [24] [25]

Heuristic search

In addition to the highly specialized domain-specific sort of knowledge that we will see later utilized in professional systems, early symbolic AI scientists found another more general application of understanding. These were called heuristics, general rules that direct a search in promising instructions: “How can non-enumerative search be useful when the underlying issue is significantly tough? The method advocated by Simon and Newell is to employ heuristics: fast algorithms that may fail on some inputs or output suboptimal solutions.” [26] Another crucial advance was to find a method to use these heuristics that ensures a solution will be found, if there is one, not standing up to the occasional fallibility of heuristics: “The A * algorithm provided a basic frame for total and optimal heuristically directed search. A * is utilized as a subroutine within almost every AI algorithm today but is still no magic bullet; its warranty of completeness is bought at the expense of worst-case rapid time. [26]

Early deal with understanding representation and reasoning

Early work covered both applications of official thinking highlighting first-order reasoning, together with attempts to handle common-sense reasoning in a less official manner.

Modeling official thinking with logic: the “neats”

Unlike Simon and Newell, John McCarthy felt that machines did not require to mimic the precise systems of human thought, however could instead search for the essence of abstract thinking and analytical with logic, [27] despite whether individuals utilized the very same algorithms. [a] His laboratory at Stanford (SAIL) focused on using formal logic to solve a broad range of issues, consisting of understanding representation, preparation and knowing. [31] Logic was likewise the focus of the work at the University of Edinburgh and in other places in Europe which resulted in the advancement of the shows language Prolog and the science of reasoning programs. [32] [33]

Modeling implicit common-sense knowledge with frames and scripts: the “scruffies”

Researchers at MIT (such as Marvin Minsky and Seymour Papert) [34] [35] [6] discovered that resolving hard issues in vision and natural language processing needed ad hoc solutions-they argued that no easy and general principle (like reasoning) would capture all the elements of smart habits. Roger Schank described their “anti-logic” methods as “scruffy” (rather than the “neat” paradigms at CMU and Stanford). [36] [37] Commonsense understanding bases (such as Doug Lenat’s Cyc) are an example of “shabby” AI, given that they must be built by hand, one complex concept at a time. [38] [39] [40]

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

The very first AI winter was a shock:

During the first AI summer season, numerous people thought that maker intelligence might be attained in simply a few years. The Defense Advance Research Projects Agency (DARPA) released programs to support AI research study to use AI to solve issues of nationwide security; in particular, to automate the translation of Russian to English for intelligence operations and to create autonomous tanks for the battleground. Researchers had started to recognize that accomplishing AI was going to be much harder than was supposed a decade previously, but a mix of hubris and disingenuousness led lots of 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 dramatic backlash set in. New DARPA leadership canceled existing AI financing programs.

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

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

Knowledge-based systems

As restrictions with weak, domain-independent approaches became increasingly more obvious, [42] researchers from all 3 customs started to build understanding into AI applications. [43] [7] The knowledge transformation was driven by the awareness that knowledge underlies high-performance, domain-specific AI applications.

Edward Feigenbaum said:

– “In the understanding lies the power.” [44] to describe that high efficiency in a particular domain requires both basic and extremely domain-specific understanding. Ed Feigenbaum and Doug Lenat called this The Knowledge Principle:

( 1) The Knowledge Principle: if a program is to perform an intricate task well, it must know a good deal about the world in which it operates.
( 2) A plausible extension of that principle, called the Breadth Hypothesis: there are 2 extra capabilities needed for smart behavior in unexpected circumstances: falling back on significantly general understanding, and analogizing to particular but distant knowledge. [45]

Success with professional systems

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

Key professional systems were:

DENDRAL, which discovered the structure of natural particles from their chemical formula and mass spectrometer readings.
MYCIN, which diagnosed bacteremia – and recommended further lab tests, when necessary – by interpreting lab results, client history, and medical professional observations. “With about 450 rules, MYCIN had the ability to perform in addition to some specialists, and considerably better than junior doctors.” [49] INTERNIST and CADUCEUS which dealt with internal medicine diagnosis. Internist attempted to capture the expertise of the chairman of internal medication at the University of Pittsburgh School of Medicine while CADUCEUS might ultimately diagnose approximately 1000 various illness.
– GUIDON, which demonstrated how a knowledge base built for expert issue solving could be repurposed for mentor. [50] XCON, to set up VAX computer systems, a then laborious process that could use up to 90 days. XCON lowered the time to about 90 minutes. [9] DENDRAL is thought about the first specialist system that count 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 interested in computer-based models of mind was Joshua Lederberg, the 1958 Nobel Prize winner in genetics. When I informed him I desired an induction “sandbox”, he said, “I have just the one for you.” His lab 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 approaches, and he had an algorithm that was proficient at generating the chemical issue area.

We did not have a grandiose vision. We worked bottom up. Our chemist was Carl Djerassi, inventor of the chemical behind the birth control pill, and likewise one of the world’s most appreciated mass spectrometrists. Carl and his postdocs were world-class professionals in mass spectrometry. We started to contribute to their knowledge, creating knowledge of engineering as we went along. These experiments totaled up to titrating DENDRAL a growing number of knowledge. The more you did that, the smarter the program became. We had very good results.

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

The other expert systems pointed out above followed DENDRAL. MYCIN exemplifies the traditional specialist system architecture of a knowledge-base of guidelines combined to a symbolic thinking system, including the usage of certainty aspects to deal with unpredictability. GUIDON demonstrates how a specific understanding base can be repurposed for a second application, tutoring, and is an example of a smart tutoring system, a specific kind of knowledge-based application. Clancey revealed that it was not sufficient simply to use MYCIN’s rules for instruction, however that he also required to include rules for discussion management and trainee modeling. [50] XCON is significant due to the fact that of the millions of dollars it conserved DEC, which activated the expert system boom where most all major corporations in the US had professional systems groups, to catch corporate competence, preserve it, and automate it:

By 1988, DEC’s AI group had 40 professional systems deployed, with more en route. DuPont had 100 in use and 500 in development. Nearly every significant U.S. corporation had its own Al group and was either utilizing or examining specialist systems. [49]

Chess expert understanding was encoded in Deep Blue. In 1996, this allowed IBM’s Deep Blue, with the aid 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 expert systems

An essential component of the system architecture for all specialist systems is the knowledge base, which shops facts and guidelines for analytical. [53] The simplest method for an expert system understanding base is simply a collection or network of production rules. Production guidelines connect symbols in a relationship comparable to an If-Then declaration. The expert system processes the rules to make reductions and to identify what extra info it requires, i.e. what questions to ask, utilizing human-readable signs. For instance, OPS5, CLIPS and their successors Jess and Drools operate in this fashion.

Expert systems can run in either a forward chaining – from evidence to conclusions – or backward chaining – from objectives to needed data and requirements – way. Advanced knowledge-based systems, such as Soar can likewise carry out meta-level thinking, that is thinking about their own thinking in regards to deciding how to solve problems and monitoring the success of analytical strategies.

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 solve a problem. The issue is represented in numerous levels of abstraction or alternate views. The specialists (knowledge sources) offer their services whenever they acknowledge they can contribute. Potential analytical actions are represented on a program that is upgraded as the problem situation modifications. A controller chooses how useful each contribution is, and who ought to make the next problem-solving action. One example, the BB1 blackboard architecture [54] was initially motivated by research studies of how people plan to carry out several jobs in a trip. [55] An innovation of BB1 was to use the exact same blackboard model to solving its control issue, i.e., its controller performed meta-level reasoning with knowledge sources that kept track of how well a strategy or the problem-solving was proceeding and could change from one method to another as conditions – such as objectives or times – altered. BB1 has been applied in several domains: building website preparation, intelligent tutoring systems, and real-time patient monitoring.

The 2nd AI winter, 1988-1993

At the height of the AI boom, business such as Symbolics, LMI, and Texas Instruments were selling LISP devices particularly targeted to accelerate the advancement of AI applications and research. In addition, numerous expert system companies, such as Teknowledge and Inference Corporation, were selling skilled system shells, training, and consulting to corporations.

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

Many reasons can be provided for the arrival of the second AI winter season. The hardware companies stopped working when much more economical general Unix workstations from Sun together with good compilers for LISP and Prolog came onto the marketplace. Many commercial implementations of professional systems were ceased when they proved too costly to preserve. Medical specialist systems never captured on for several factors: the trouble in keeping them as much as date; the difficulty for doctor to learn how to use a bewildering variety of various specialist systems for different medical conditions; and possibly most crucially, the unwillingness of doctors to rely on a computer-made medical diagnosis over their gut instinct, even for specific domains where the specialist systems could outperform a typical physician. Venture capital money deserted AI practically overnight. The world AI conference IJCAI hosted a huge and lavish trade convention and countless nonacademic guests in 1987 in Vancouver; the primary AI conference the following year, AAAI 1988 in St. Paul, was a little and strictly scholastic affair. [9]

Including more rigorous structures, 1993-2011

Uncertain thinking

Both statistical approaches and extensions to logic were attempted.

One analytical method, hidden Markov models, had actually currently been promoted in the 1980s for speech recognition work. [11] Subsequently, in 1988, Judea Pearl popularized using Bayesian Networks as a noise but efficient method of managing unsure reasoning with his publication of the book Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. [56] and Bayesian approaches were applied successfully in expert systems. [57] Even later on, in the 1990s, analytical relational learning, a technique that combines possibility with sensible formulas, enabled possibility to be combined with first-order logic, e.g., with either Markov Logic Networks or Probabilistic Soft Logic.

Other, non-probabilistic extensions to first-order reasoning to assistance were likewise attempted. For example, non-monotonic reasoning could be utilized with truth upkeep systems. A truth maintenance system tracked presumptions and reasons for all reasonings. It permitted inferences to be withdrawn when assumptions were learnt to be incorrect or a contradiction was obtained. Explanations could be offered an inference by discussing which guidelines were used to develop it and after that continuing through underlying reasonings and guidelines all the way back to root presumptions. [58] Lofti Zadeh had presented a various kind of extension to deal with the representation of vagueness. For instance, in deciding how “heavy” or “tall” a male is, there is often no clear “yes” or “no” answer, and a predicate for heavy or tall would instead return values between 0 and 1. Those values represented to what degree the predicates held true. His fuzzy logic even more provided a method for propagating mixes of these values through logical formulas. [59]

Machine knowing

Symbolic machine learning approaches were examined to deal with the understanding acquisition bottleneck. Among the earliest is Meta-DENDRAL. Meta-DENDRAL used a generate-and-test technique to generate plausible rule hypotheses to test versus spectra. Domain and job knowledge reduced the variety of prospects tested to a manageable size. Feigenbaum described Meta-DENDRAL as

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

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

Advances were made in understanding artificial intelligence theory, too. Tom Mitchell presented version space learning which explains learning as an explore an area of hypotheses, with upper, more basic, and lower, more specific, boundaries including all practical hypotheses consistent with the examples seen up until now. [62] More formally, Valiant presented Probably Approximately Correct Learning (PAC Learning), a structure for the mathematical analysis of artificial intelligence. [63]

Symbolic device learning encompassed more than learning by example. E.g., John Anderson supplied a cognitive model of human knowing where ability practice results in a collection of rules from a declarative format to a procedural format with his ACT-R cognitive architecture. For example, a trainee might learn to apply “Supplementary angles are 2 angles whose measures sum 180 degrees” as numerous various procedural rules. E.g., one rule might state that if X and Y are additional and you understand X, then Y will be 180 – X. He called his method “knowledge compilation”. ACT-R has actually been used successfully to model aspects of human cognition, such as learning and retention. ACT-R is likewise used in smart tutoring systems, called cognitive tutors, to successfully teach geometry, computer programs, and algebra to school kids. [64]

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

As an alternative to reasoning, Roger Schank introduced case-based reasoning (CBR). The CBR method outlined in his book, Dynamic Memory, [67] focuses first on keeping in mind crucial problem-solving cases for future usage and generalizing them where appropriate. When confronted with a brand-new issue, CBR retrieves the most comparable previous case and adapts it to the specifics of the current issue. [68] Another option to reasoning, genetic algorithms and hereditary shows are based on an evolutionary design of learning, where sets of guidelines are encoded into populations, the guidelines govern the habits of individuals, and selection of the fittest prunes out sets of inappropriate guidelines over lots of generations. [69]

Symbolic device learning was used to finding out concepts, guidelines, heuristics, and analytical. Approaches, aside from those above, include:

1. Learning from direction or advice-i.e., taking human instruction, posed as guidance, and figuring out how to operationalize it in specific circumstances. For instance, in a video game of Hearts, learning precisely how to play a hand to “avoid taking points.” [70] 2. Learning from exemplars-improving efficiency by accepting subject-matter specialist (SME) feedback during training. When problem-solving stops working, querying the professional to either find out a brand-new prototype for problem-solving or to find out a new description as to exactly why one prototype is more relevant than another. For example, the program Protos learned to diagnose tinnitus cases by interacting with an audiologist. [71] 3. Learning by analogy-constructing issue options based upon similar issues seen in the past, and then modifying their options to fit a brand-new circumstance or domain. [72] [73] 4. Apprentice learning systems-learning unique options to issues by observing human analytical. Domain knowledge discusses why novel options are appropriate and how the option can be generalized. LEAP learned how to design VLSI circuits by observing human designers. [74] 5. Learning by discovery-i.e., developing tasks to perform experiments and then discovering from the outcomes. Doug Lenat’s Eurisko, for instance, learned heuristics to beat human gamers at the Traveller role-playing game for two years in a row. [75] 6. Learning macro-operators-i.e., browsing for beneficial macro-operators to be gained from sequences of standard problem-solving actions. Good macro-operators simplify analytical by enabling problems to be fixed 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 been compared to deep knowing as complementary “… with parallels having been drawn lot of times by AI scientists between Kahneman’s research on human thinking and choice 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 explanation while deep knowing is more apt for quick pattern acknowledgment in perceptual applications with loud data. [17] [18]

Neuro-symbolic AI: integrating neural and symbolic techniques

Neuro-symbolic AI efforts to incorporate neural and symbolic architectures in a manner that addresses strengths and weak points of each, in a complementary fashion, in order to support robust AI efficient in thinking, discovering, and cognitive modeling. As argued by Valiant [77] and numerous others, [78] the effective building of rich computational cognitive designs demands the combination of sound symbolic reasoning and effective (maker) knowing designs. Gary Marcus, similarly, argues that: “We can not build abundant cognitive designs in an adequate, automated way without the set of three of hybrid architecture, rich anticipation, and sophisticated techniques for thinking.”, [79] and in particular: “To build a robust, knowledge-driven method to AI we must have the equipment of symbol-manipulation in our toolkit. Too much of helpful knowledge is abstract to make do without tools that represent and manipulate abstraction, and to date, the only equipment that we understand of that can manipulate such abstract understanding dependably is the apparatus of sign control. ” [80]

Henry Kautz, [19] Francesca Rossi, [81] and Bart Selman [82] have likewise argued for a synthesis. Their arguments are based upon a requirement to address the 2 kinds of believing talked about in Daniel Kahneman’s book, Thinking, Fast and Slow. Kahneman describes human thinking as having 2 elements, System 1 and System 2. System 1 is quickly, automated, instinctive and unconscious. System 2 is slower, step-by-step, and explicit. System 1 is the kind used for pattern acknowledgment while System 2 is far much better matched for preparation, reduction, and deliberative thinking. In this view, deep knowing finest designs the first kind of believing while symbolic reasoning best designs the 2nd kind and both are required.

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

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 been pursued by a relatively small research study neighborhood over the last twenty years and has yielded numerous considerable outcomes. Over the last years, neural symbolic systems have been shown capable of overcoming the so-called propositional fixation of neural networks, as McCarthy (1988) put it in reaction to Smolensky (1988 ); see also (Hinton, 1990). Neural networks were shown 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 number of problems in the areas of bioinformatics, control engineering, software application verification and adjustment, visual intelligence, ontology knowing, and video game. [78]

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

– Symbolic Neural symbolic-is the existing method of lots of neural designs in natural language processing, where words or subword tokens are both the supreme input and output of large language models. Examples consist of BERT, RoBERTa, and GPT-3.
– Symbolic [Neural] -is exemplified by AlphaGo, where symbolic methods are used to call neural strategies. In this case the symbolic technique is Monte Carlo tree search and the neural techniques discover how to examine video game positions.
– Neural|Symbolic-uses a neural architecture to interpret affective information 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 consequently discovered by a deep knowing design, e.g., to train a neural model for symbolic computation by using a Macsyma-like symbolic mathematics system to develop or identify examples.
– Neural _ Symbolic -uses a neural net that is generated 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] -allows a neural model to straight call a symbolic thinking engine, e.g., to perform an action or assess a state.

Many key research study concerns stay, such as:

– What is the very best method to integrate neural and symbolic architectures? [87]- How should symbolic structures be represented within neural networks and extracted from them?
– How should sensible knowledge be learned and reasoned about?
– How can abstract understanding that is difficult to encode logically be dealt with?

Techniques and contributions

This section provides an overview of methods and contributions in a general context leading to many other, more comprehensive posts in Wikipedia. Sections on Artificial Intelligence and Uncertain Reasoning are covered earlier in the history section.

AI shows languages

The key AI shows language in the US throughout the last symbolic AI boom period was LISP. LISP is the second earliest programming language after FORTRAN and was created in 1958 by John McCarthy. LISP provided the very first read-eval-print loop to support fast program development. Compiled functions might be easily combined with interpreted functions. Program tracing, stepping, and breakpoints were also provided, in addition to the capability to alter values or functions and continue from breakpoints or mistakes. It had the first self-hosting compiler, suggesting that the compiler itself was initially composed in LISP and then ran interpretively to compile the compiler code.

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

Garbage collection
Dynamic typing
Higher-order functions
Recursion
Conditionals

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

In contrast to the US, in Europe the crucial AI programs language throughout that exact same duration was Prolog. Prolog supplied a built-in store of realities and provisions that could be queried by a read-eval-print loop. The shop might serve as an understanding base and the stipulations could act as rules or a restricted kind of reasoning. As a subset of first-order logic Prolog was based upon Horn provisions with a closed-world assumption-any facts not known were considered false-and an unique name assumption for primitive terms-e.g., the identifier barack_obama was considered to refer to precisely one object. Backtracking and marriage are built-in to Prolog.

Alain Colmerauer and Philippe Roussel are credited as the inventors of Prolog. Prolog is a type of reasoning programming, which was created by Robert Kowalski. Its history was likewise affected by Carl Hewitt’s PLANNER, an assertional database with pattern-directed invocation of approaches. For more information see the section on the origins of Prolog in the PLANNER post.

Prolog is likewise a sort of declarative programming. The logic clauses that describe programs are straight interpreted to run the programs specified. No explicit series of actions is required, as is the case with vital programming languages.

Japan promoted Prolog for its Fifth Generation Project, meaning to build unique hardware for high efficiency. Similarly, LISP makers were developed to run LISP, however as the second AI boom turned to bust these companies might not compete with brand-new workstations that could now run LISP or Prolog natively at comparable speeds. See the history section for more information.

Smalltalk was another influential AI programming language. For instance, it introduced metaclasses and, in addition to Flavors and CommonLoops, influenced 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 allows several inheritance, in addition to incremental extensions to both classes and metaclasses, hence providing a run-time meta-object procedure. [88]

For other AI programs languages see this list of shows languages for expert system. Currently, Python, a multi-paradigm programming language, is the most popular programs 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, functional aspects such as higher-order functions, and object-oriented shows that includes metaclasses.

Search

Search arises in numerous type of problem solving, consisting of preparation, restriction satisfaction, and playing video games such as checkers, chess, and go. The very best understood 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 reasoning

Multiple different methods to represent knowledge and after that reason with those representations have actually been examined. Below is a quick introduction of approaches to understanding representation and automated thinking.

Knowledge representation

Semantic networks, conceptual graphs, frames, and logic are all approaches to modeling understanding such as domain understanding, problem-solving understanding, and the semantic significance of language. Ontologies model key ideas 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 viewed as an ontology. YAGO integrates WordNet as part of its ontology, to align truths drawn out from Wikipedia with WordNet synsets. The Disease Ontology is an example of a medical ontology presently being utilized.

Description logic is a logic for automated classification of ontologies and for detecting inconsistent category information. OWL is a language used to represent ontologies with description logic. Protégé is an ontology editor that can check out in OWL ontologies and then check 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 below can prove theorems in first-order logic. Horn clause logic is more limited than first-order logic and is utilized in logic programming languages such as Prolog. Extensions to first-order logic consist of temporal logic, to deal with time; epistemic reasoning, to reason about representative understanding; modal logic, to deal with possibility and necessity; and probabilistic reasonings to handle reasoning and likelihood together.

Automatic theorem proving

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

Prover9.
ACL2.
Vampire.

Prover9 can be used in conjunction with the Mace4 model checker. ACL2 is a theorem prover that can deal with proofs by induction and is a descendant of the Boyer-Moore Theorem Prover, likewise understood as Nqthm.

Reasoning in knowledge-based systems

Knowledge-based systems have a specific knowledge base, typically of guidelines, to improve reusability across domains by separating procedural code and domain understanding. A different inference engine processes guidelines and includes, deletes, or customizes a knowledge store.

Forward chaining reasoning engines are the most common, and are seen in CLIPS and OPS5. Backward chaining occurs in Prolog, where a more restricted logical representation is used, Horn Clauses. Pattern-matching, particularly unification, is used in Prolog.

A more versatile type of analytical occurs when thinking about what to do next occurs, rather than simply picking one of the readily available actions. This type of meta-level thinking is utilized in Soar and in the BB1 blackboard architecture.

Cognitive architectures such as ACT-R may have extra capabilities, such as the capability to compile frequently utilized knowledge into higher-level chunks.

Commonsense thinking

Marvin Minsky initially proposed frames as a way of analyzing common visual situations, such as a workplace, and Roger Schank extended this concept to scripts for typical routines, such as eating in restaurants. Cyc has actually tried to record useful sensible understanding and has “micro-theories” to deal with particular kinds of domain-specific reasoning.

Qualitative simulation, such as Benjamin Kuipers’s QSIM, [90] estimates human reasoning about ignorant physics, such as what occurs when we heat a liquid in a pot on the range. We anticipate it to heat and perhaps boil over, even though we might not know its temperature level, its boiling point, or other information, such as air pressure.

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

Constraints and constraint-based reasoning

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

Automated planning

The General Problem Solver (GPS) cast preparation as problem-solving used means-ends analysis to create strategies. STRIPS took a different method, seeing preparation as theorem proving. Graphplan takes a least-commitment method to planning, rather than sequentially choosing actions from an initial state, working forwards, or a goal state if working backwards. Satplan is a method to preparing where a planning problem is decreased to a Boolean satisfiability problem.

Natural language processing

Natural language processing concentrates on treating language as information to carry out jobs such as identifying subjects without always comprehending the desired meaning. Natural language understanding, on the other hand, constructs a significance representation and utilizes that for more processing, such as answering questions.

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 since improved by deep learning techniques. In symbolic AI, discourse representation theory and first-order logic have actually 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 elements are interpretable as principles named by Wikipedia posts.

New deep knowing techniques based on Transformer models have now eclipsed these earlier symbolic AI methods and attained cutting edge performance in natural language processing. However, Transformer designs 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 elements is nontransparent.

Agents and multi-agent systems

Agents are autonomous systems embedded in an environment they perceive and act on in some sense. Russell and Norvig’s basic textbook on expert system is arranged to show representative architectures of increasing sophistication. [91] The elegance of agents differs from simple reactive agents, to those with a model of the world and automated preparation capabilities, potentially a BDI representative, i.e., one with beliefs, desires, and intentions – or alternatively a reinforcement finding out model learned in time to choose actions – up to a combination of alternative architectures, such as a neuro-symbolic architecture [87] that consists of deep learning for understanding. [92]

In contrast, a multi-agent system consists of several representatives that interact amongst themselves with some inter-agent communication language such as Knowledge Query and Manipulation Language (KQML). The agents need not all have the exact same internal architecture. Advantages of multi-agent systems include the ability to divide work amongst the representatives and to increase fault tolerance when representatives are lost. Research issues consist of how agents reach agreement, distributed problem fixing, multi-agent learning, multi-agent preparation, and dispersed restraint optimization.

Controversies occurred from at an early stage in symbolic AI, both within the field-e.g., between logicists (the pro-logic “neats”) and non-logicists (the anti-logic “scruffies”)- and in between those who embraced AI but declined symbolic approaches-primarily connectionists-and those outside the field. Critiques from exterior of the field were primarily from philosophers, on intellectual premises, however also from financing companies, particularly throughout the two AI winters.

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

Limitations were discovered in utilizing easy first-order reasoning to factor about dynamic domains. Problems were found both with regards to enumerating the prerequisites for an action to be successful and in providing axioms for what did not alter 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] A simple example happens in “proving that one person might 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 needed for the reduction to succeed. Similar axioms would be required for other domain actions to define what did not change.

A similar issue, called the Qualification Problem, occurs in trying to specify the prerequisites for an action to prosper. A limitless variety of pathological conditions can be envisioned, e.g., a banana in a tailpipe might prevent a cars and truck from running properly.

McCarthy’s technique to repair the frame issue was circumscription, a type of non-monotonic logic where reductions might be made from actions that require only specify what would change while not having to explicitly specify everything that would not change. Other non-monotonic logics supplied truth maintenance systems that modified beliefs resulting in contradictions.

Other ways of handling more open-ended domains consisted of probabilistic reasoning systems and artificial intelligence to learn new concepts and guidelines. McCarthy’s Advice Taker can be seen as a motivation here, as it might include brand-new understanding supplied by a human in the kind of assertions or guidelines. For instance, speculative symbolic machine discovering systems checked out the capability to take high-level natural language advice and to translate it into domain-specific actionable rules.

Similar to the issues in dealing with dynamic domains, sensible reasoning is also tough to catch in formal reasoning. Examples of common-sense reasoning include implicit reasoning about how people believe or general understanding of daily occasions, things, and living animals. This type of understanding is considered given and not considered as noteworthy. Common-sense reasoning is an open location of research study and challenging both for symbolic systems (e.g., Cyc has attempted to record crucial parts of this understanding over more than a decade) and neural systems (e.g., self-driving vehicles that do not know not to drive into cones or not to hit pedestrians strolling a bicycle).

McCarthy viewed his Advice Taker as having sensible, however his definition of common-sense was various than the one above. [94] He defined a program as having typical sense “if it instantly deduces for itself a sufficiently wide class of instant repercussions of anything it is informed and what it currently knows. “

Connectionist AI: philosophical difficulties and sociological disputes

Connectionist techniques include earlier deal with neural networks, [95] such as perceptrons; work 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 approaches, such as Transformers, GANs, and other work in deep learning.

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

1. Implementationism-where connectionist architectures execute the abilities for symbolic processing,
2. Radical connectionism-where symbolic processing is turned down totally, and connectionist architectures underlie intelligence and are completely enough 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 debates within the neural network community, described the moderate connectionism consider as basically compatible with existing 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 eclectic view of the existing debate in between connectionism and symbolic AI. Among the scientists who has actually elaborated this position most explicitly is Andy Clark, a thinker from the School of Cognitive and Computing Sciences of the University of Sussex (Brighton, England). Clark protected hybrid (partially symbolic, partly connectionist) systems. He claimed that (a minimum of) two kinds of theories are required in order to study and design cognition. On the one hand, for some information-processing tasks (such as pattern acknowledgment) connectionism has advantages over symbolic designs. But on the other hand, for other cognitive procedures (such as serial, deductive reasoning, and generative sign adjustment processes) the symbolic paradigm provides sufficient designs, and not only “approximations” (contrary to what radical connectionists would declare). [97]

Gary Marcus has actually declared that the animus in the deep knowing neighborhood against symbolic methods now may be more sociological than philosophical:

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

And yet, for the most part, that’s how most existing AI earnings. Hinton and numerous others have attempted hard to get rid of symbols entirely. The deep learning hope-seemingly grounded not so much in science, but in a sort of historic grudge-is that smart behavior will emerge simply from the confluence of massive data and deep knowing. Where classical computer systems and software application resolve tasks by defining sets of symbol-manipulating guidelines committed to particular tasks, such as editing a line in a word processor or performing an estimation in a spreadsheet, neural networks typically attempt to fix jobs by analytical approximation and gaining from examples.

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

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

…

Ever since, his anti-symbolic project has just increased in strength. In 2016, Yann LeCun, Bengio, and Hinton composed a manifesto for deep knowing in one of science’s essential journals, Nature. It closed with a direct attack on symbol adjustment, calling not for reconciliation however for straight-out replacement. Later, Hinton told a gathering of European Union leaders that investing any further money in symbol-manipulating methods was “a big mistake,” likening it to purchasing internal combustion engines in the era of electrical cars and trucks. [98]

Part of these disputes may be because of unclear terminology:

Turing award winner Judea Pearl offers a critique of artificial intelligence which, sadly, conflates the terms maker learning and deep learning. Similarly, when Geoffrey Hinton describes symbolic AI, the undertone of the term tends to be that of specialist systems dispossessed of any ability to find out. Using the terms requires information. Artificial intelligence is not confined to association rule mining, c.f. the body of work on symbolic ML and relational knowing (the differences to deep learning being the option of representation, localist logical rather than distributed, and the non-use of gradient-based learning algorithms). Equally, symbolic AI is not just about production rules composed by hand. An appropriate definition of AI concerns knowledge representation and reasoning, self-governing multi-agent systems, preparation and argumentation, along with learning. [99]

Situated robotics: the world as a model

Another critique of symbolic AI is the embodied cognition technique:

The embodied cognition technique claims that it makes no sense to think about the brain individually: cognition happens 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, including the rest of its body. Under the embodied cognition method, robotics, vision, and other sensors become central, not peripheral. [100]

Rodney Brooks invented behavior-based robotics, one method to embodied cognition. Nouvelle AI, another name for this approach, is viewed as an alternative to both symbolic AI and connectionist AI. His approach rejected representations, either symbolic or dispersed, as not just unnecessary, but as harmful. Instead, he developed the subsumption architecture, a layered architecture for embodied representatives. Each layer attains a various purpose and should function in the genuine world. For instance, the very first robotic he describes in Intelligence Without Representation, has 3 layers. The bottom layer interprets finder sensors to avoid objects. The middle layer causes the robot to wander around when there are no barriers. The leading layer causes the robotic to go to more far-off locations for more expedition. Each layer can momentarily prevent or reduce a lower-level layer. He criticized AI researchers for specifying AI problems for their systems, when: “There is no clean department in between understanding (abstraction) and reasoning in the real life.” [101] He called his robotics “Creatures” and each layer was “made up of a fixed-topology network of simple limited state makers.” [102] In the Nouvelle AI method, “First, it is essential to check the Creatures we develop in the real life; i.e., in the very same world that we human beings inhabit. It is dreadful to fall under the temptation of evaluating them in a simplified world first, even with the very best intents of later moving activity to an unsimplified world.” [103] His emphasis on real-world screening remained in contrast to “Early work in AI focused on video games, geometrical problems, 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 benefits, however has actually been criticized by the other methods. Symbolic AI has been criticized as disembodied, liable to the credentials issue, and bad in handling the affective problems where deep discovering excels. In turn, connectionist AI has been criticized as inadequately fit for deliberative detailed issue fixing, incorporating knowledge, and handling preparation. Finally, Nouvelle AI stands out in reactive and real-world robotics domains but has been slammed for problems in integrating knowing and knowledge.

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

Overall, Dreyfus saw areas where AI did not have complete answers and stated that Al is therefore impossible; we now see much of these very same areas undergoing ongoing research study and development causing increased ability, not impossibility. [100]

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

Notes

^ McCarthy once stated: “This is AI, so we do not care if it’s mentally genuine”. [4] McCarthy repeated his position in 2006 at the AI@50 conference where he said “Artificial intelligence is not, by definition, simulation of human intelligence”. [28] Pamela McCorduck writes that there are “2 major branches of artificial intelligence: one aimed at producing intelligent habits no matter how it was achieved, and the other aimed at modeling smart procedures 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 ‘devices that fly so precisely like pigeons that they can trick even other pigeons.'” [30] Citations

^ Garnelo, Marta; Shanahan, Murray (October 2019). “Reconciling deep knowing with symbolic expert system: representing things 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 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. 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 errors”. 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 limits of understanding”. Proceedings of the International Workshop on Expert System 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”. Artificial Intelligence. 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 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 City: 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 Knowing 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 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 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 Expert System) (Hardcover ed.).
Crevier, Daniel (1993 ). AI: The Tumultuous Look 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: 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 ), Artificial Intelligence: 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 Science Technical Reports. 76. p. 6.
Honavar, Vasant (1995 ). Symbolic Artificial Intelligence 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 Point of view”. 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 typical 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 initial on 3 January 2007. Retrieved 16 October 2008.
Marcus, Gary; Davis, Ernest (2019 ). Rebooting AI: Building Artificial Intelligence We Can Trust. New York: 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 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 Artificial Intelligence”. 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 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 ). 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 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, 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 Technology (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 Artificial Intelligence and Further On.