
Arentiaseguros
Ajouter un avis SuivezVue d'ensemble
-
Date de création décembre 3, 1992
-
Secteur Environnenent
-
Offres d'emploi 0
-
Consultés 8
Company Description
Symbolic Expert System
In expert system, symbolic artificial intelligence (also called classical expert system or logic-based artificial intelligence) [1] [2] is the term for the collection of all methods in artificial intelligence research study that are based upon top-level symbolic (human-readable) representations of problems, reasoning and search. [3] Symbolic AI used tools such as logic programming, production rules, semantic nets 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 preparation and scheduling systems. The Symbolic AI paradigm resulted in critical ideas in search, symbolic programming languages, agents, multi-agent systems, the semantic web, and the strengths and limitations of formal understanding and thinking 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 encouraged that symbolic techniques would eventually succeed in creating a maker with synthetic general intelligence and considered this the ultimate objective of their field. [citation required] An early boom, with early successes such as the Logic Theorist and Samuel’s Checkers Playing Program, resulted in unrealistic expectations and promises and was followed by the first AI Winter as funding dried up. [5] [6] A 2nd boom (1969-1986) occurred with the increase of expert systems, their pledge of recording business expertise, and an enthusiastic corporate welcome. [7] [8] That boom, and some early successes, e.g., with XCON at DEC, was followed again by later on dissatisfaction. [8] Problems with difficulties in understanding acquisition, maintaining large understanding bases, and brittleness in dealing with out-of-domain issues occurred. Another, 2nd, AI Winter (1988-2011) followed. [9] Subsequently, AI researchers focused on dealing with hidden issues in handling unpredictability and in understanding acquisition. [10] Uncertainty was attended to with formal approaches such as surprise Markov models, Bayesian reasoning, and statistical relational learning. [11] [12] Symbolic machine discovering resolved the understanding acquisition issue with contributions consisting of Version Space, Valiant’s PAC knowing, Quinlan’s ID3 decision-tree knowing, case-based knowing, and inductive logic shows to learn relations. [13]
Neural networks, a subsymbolic method, had actually 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 work in convolutional neural networks by LeCun et al. in 1989. [15] However, neural networks were not considered as successful until about 2012: « Until Big Data became commonplace, the general agreement in the Al neighborhood was that the so-called neural-network approach was hopeless. Systems simply didn’t work that well, compared to other methods. … A transformation came in 2012, when a number of individuals, consisting of a group of researchers dealing with Hinton, exercised a way to utilize the power of GPUs to enormously increase the power of neural networks. » [16] Over the next numerous years, deep knowing had amazing success in managing vision, speech recognition, speech synthesis, image generation, and machine translation. However, considering that 2020, as intrinsic difficulties with bias, description, coherence, and effectiveness ended up being more apparent with deep learning techniques; an increasing number of AI researchers have actually called for combining the very best of both the symbolic and neural network approaches [17] [18] and addressing areas that both approaches have trouble with, such as common-sense thinking. [16]
A short 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 post on the History of AI, with dates and titles differing somewhat for increased clearness.
The first AI summer season: illogical vitality, 1948-1966
Success at early efforts in AI took place in three primary locations: synthetic neural networks, knowledge representation, and heuristic search, contributing to high expectations. This section sums up Kautz’s reprise of early AI history.
Approaches inspired by human or animal cognition or habits
Cybernetic methods tried to replicate the feedback loops between animals and their environments. A robotic turtle, with sensing units, motors for driving and guiding, and 7 vacuum tubes for control, based on 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, reinforcement learning, 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 prove 38 elementary theorems from Whitehead and Russell’s Principia Mathematica. Newell, Simon, and Shaw later generalized this work to develop a domain-independent problem solver, GPS (General Problem Solver). GPS resolved problems represented with official operators through state-space search utilizing means-ends analysis. [21]
During the 1960s, symbolic techniques achieved terrific success at simulating smart behavior 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 style of research study. Earlier approaches based upon cybernetics or artificial neural networks were deserted or pushed into the background.
Herbert Simon and Allen Newell studied human problem-solving skills and attempted to formalize them, and their work laid the foundations of the field of expert system, as well as cognitive science, operations research and management science. Their research group used the outcomes of mental experiments to establish programs that simulated the strategies that people utilized to fix issues. [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 knowledge that we will see later used in specialist systems, early symbolic AI scientists discovered another more general application of understanding. These were called heuristics, general rules that guide a search in promising instructions: « How can non-enumerative search be useful when the underlying issue is greatly hard? The approach advocated by Simon and Newell is to utilize heuristics: fast algorithms that may fail on some inputs or output suboptimal options. » [26] Another crucial advance was to find a way to use these heuristics that ensures a solution will be found, if there is one, not holding up against the occasional fallibility of heuristics: « The A * algorithm offered a basic frame for total and optimal heuristically guided search. A * is utilized as a subroutine within almost every AI algorithm today however is still no magic bullet; its warranty of efficiency is bought at the expense of worst-case exponential time. [26]
Early work on knowledge representation and reasoning
Early work covered both applications of official reasoning stressing first-order logic, in addition to attempts to handle sensible thinking in a less official way.
Modeling official reasoning with reasoning: the « neats »
Unlike Simon and Newell, John McCarthy felt that machines did not require to replicate the precise systems of human idea, but could rather attempt to discover the essence of abstract reasoning and problem-solving with reasoning, [27] despite whether people used the same algorithms. [a] His lab at Stanford (SAIL) concentrated on using formal logic to solve a variety of problems, consisting of understanding representation, preparation and knowing. [31] Logic was likewise the focus of the work at the University of Edinburgh and elsewhere in Europe which led to the advancement of the programming language Prolog and the science of reasoning programming. [32] [33]
Modeling implicit common-sense understanding with frames and scripts: the « scruffies »
Researchers at MIT (such as Marvin Minsky and Seymour Papert) [34] [35] [6] found that resolving difficult 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 aspects of smart behavior. Roger Schank described their « anti-logic » approaches as « scruffy » (as opposed to the « cool » paradigms at CMU and Stanford). [36] [37] Commonsense knowledge bases (such as Doug Lenat’s Cyc) are an example of « shabby » AI, given that they must be constructed by hand, one complicated idea at a time. [38] [39] [40]
The first AI winter season: crushed dreams, 1967-1977
The first AI winter was a shock:
During the very first AI summer, lots of individuals believed that machine intelligence could be achieved in simply a few years. The Defense Advance Research Projects Agency (DARPA) released programs to support AI research study to utilize AI to solve problems of national security; in particular, 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 understand that accomplishing AI was going to be much harder than was supposed a decade earlier, but a mix of hubris and disingenuousness led lots of university and think-tank researchers to accept financing with promises of deliverables that they must have known they might not satisfy. By the mid-1960s neither helpful natural language translation systems nor autonomous tanks had actually been developed, and a remarkable reaction embeded in. New DARPA leadership canceled existing AI financing programs.
Outside of the United States, the most fertile ground for AI research study was the United Kingdom. The AI winter season in the United Kingdom was stimulated on not so much by dissatisfied military leaders as by rival academics who saw AI scientists as charlatans and a drain on research financing. A professor of used mathematics, Sir James Lighthill, was commissioned by Parliament to examine the state of AI research in the country. The report specified that all of the problems being dealt with in AI would be much better dealt with by researchers from other disciplines-such as applied mathematics. The report also declared that AI successes on toy problems might never scale to real-world applications due to combinatorial surge. [41]
The second AI summer season: understanding is power, 1978-1987
Knowledge-based systems
As limitations with weak, domain-independent approaches ended up being more and more obvious, [42] scientists from all 3 customs began to construct understanding into AI applications. [43] [7] The understanding transformation was driven by the realization that knowledge underlies high-performance, domain-specific AI applications.
Edward Feigenbaum stated:
– « In the understanding lies the power. » [44]
to describe that high performance in a specific domain requires both general and highly domain-specific knowledge. Ed Feigenbaum and Doug Lenat called this The Knowledge Principle:
( 1) The Knowledge Principle: if a program is to perform a complicated task well, it must understand a terrific offer about the world in which it operates.
( 2) A possible extension of that concept, called the Breadth Hypothesis: there are two additional capabilities necessary for intelligent habits in unforeseen scenarios: drawing on progressively general knowledge, and analogizing to particular but distant knowledge. [45]
Success with specialist 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. [46] [47] [48]
Key specialist systems were:
DENDRAL, which discovered the structure of organic particles from their chemical formula and mass spectrometer readings.
MYCIN, which diagnosed bacteremia – and recommended additional lab tests, when essential – by interpreting laboratory results, client history, and medical professional observations. « With about 450 guidelines, MYCIN was able to perform along with some experts, and substantially much better than junior physicians. » [49] INTERNIST and CADUCEUS which tackled internal medication diagnosis. Internist attempted to catch the knowledge of the chairman of internal medication at the University of Pittsburgh School of Medicine while CADUCEUS could ultimately detect approximately 1000 different diseases.
– GUIDON, which demonstrated how an understanding base constructed for specialist issue fixing could be repurposed for teaching. [50] XCON, to configure VAX computer systems, a then tiresome procedure that could use up to 90 days. XCON decreased the time to about 90 minutes. [9]
DENDRAL is thought about the very first specialist system that depend on knowledge-intensive problem-solving. 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 just the one for you. » His lab was doing mass spectrometry of amino acids. The question 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 began the DENDRAL Project: I was proficient at heuristic search approaches, and he had an algorithm that was proficient at producing the chemical issue space.
We did not have a grandiose vision. We worked bottom up. Our chemist was Carl Djerassi, innovator 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 specialists in mass spectrometry. We began to include to their understanding, creating understanding 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 ended up being. We had great results.
The generalization was: in the understanding lies the power. That was the big concept. In my career that is the big, « Ah ha!, » and it wasn’t the way AI was being done previously. Sounds easy, however it’s most likely AI’s most powerful generalization. [51]
The other specialist systems mentioned above followed DENDRAL. MYCIN exhibits the classic professional system architecture of a knowledge-base of rules paired to a symbolic thinking mechanism, consisting of making use of certainty elements to manage uncertainty. GUIDON shows how a specific understanding base can be repurposed for a 2nd application, tutoring, and is an example of a smart tutoring system, a particular type of knowledge-based application. Clancey showed that it was not enough simply to utilize MYCIN’s rules for instruction, however that he also required to add guidelines for discussion management and student modeling. [50] XCON is substantial due to the fact that of the millions of dollars it conserved DEC, which activated the specialist system boom where most all major corporations in the US had skilled systems groups, to capture business know-how, maintain 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 advancement. Nearly every major U.S. corporation had its own Al group and was either utilizing or investigating specialist systems. [49]
Chess specialist understanding was encoded in Deep Blue. In 1996, this enabled IBM’s Deep Blue, with the assistance of symbolic AI, to win in a game of chess versus the world champion at that time, Garry Kasparov. [52]
Architecture of knowledge-based and expert systems
A crucial part of the system architecture for all professional systems is the knowledge base, which shops realities and rules for problem-solving. [53] The easiest method for an expert system knowledge base is simply a collection or network of production guidelines. Production rules link signs in a relationship similar to an If-Then statement. The expert system processes the rules to make reductions and to determine what extra info it requires, i.e. what concerns to ask, utilizing human-readable signs. For example, OPS5, CLIPS and their successors Jess and Drools run in this fashion.
Expert systems can run in either a forward chaining – from proof to conclusions – or backwards chaining – from goals to needed data and requirements – way. More innovative knowledge-based systems, such as Soar can also carry out meta-level reasoning, that is reasoning about their own thinking in regards to choosing how to solve issues and monitoring the success of problem-solving techniques.
Blackboard systems are a second kind of knowledge-based or expert system architecture. They design a neighborhood of experts incrementally contributing, where they can, to resolve a problem. The problem is represented in numerous levels of abstraction or alternate views. The professionals (knowledge sources) volunteer their services whenever they acknowledge they can contribute. Potential problem-solving actions are represented on an agenda that is updated as the problem scenario changes. A controller chooses how helpful each contribution is, and who need to make the next problem-solving action. One example, the BB1 chalkboard architecture [54] was originally influenced by research studies of how people prepare to perform numerous tasks in a trip. [55] An innovation of BB1 was to apply the very same chalkboard design to solving its control issue, i.e., its controller carried out meta-level reasoning with knowledge sources that kept an eye on how well a plan or the problem-solving was proceeding and might switch from one method to another as conditions – such as objectives or times – altered. BB1 has actually been applied in multiple domains: building and construction website planning, smart tutoring systems, and real-time patient tracking.
The second AI winter, 1988-1993
At the height of the AI boom, companies such as Symbolics, LMI, and Texas Instruments were selling LISP makers particularly targeted to speed up the advancement of AI applications and research. In addition, numerous expert system business, such as Teknowledge and Inference Corporation, were offering expert system shells, training, and speaking with to corporations.
Unfortunately, the AI boom did not last and Kautz best explains the 2nd AI winter that followed:
Many reasons can be offered for the arrival of the second AI winter. The hardware business failed when a lot more cost-efficient general Unix workstations from Sun together with good compilers for LISP and Prolog came onto the market. Many industrial releases of specialist systems were stopped when they showed too costly to preserve. Medical expert systems never captured on for a number of factors: the difficulty in keeping them up to date; the challenge for physician to discover how to use an overwelming range of different specialist systems for different medical conditions; and perhaps most crucially, the reluctance of medical professionals to trust a computer-made diagnosis over their gut instinct, even for specific domains where the professional systems might outperform an average doctor. Venture capital money deserted AI virtually overnight. The world AI conference IJCAI hosted a massive and luxurious trade program and countless nonacademic participants in 1987 in Vancouver; the primary AI conference the list below year, AAAI 1988 in St. Paul, was a small and strictly academic affair. [9]
Adding in more extensive foundations, 1993-2011
Uncertain thinking
Both statistical approaches and extensions to logic were tried.
One statistical technique, hidden Markov designs, had actually currently been promoted in the 1980s for speech recognition work. [11] Subsequently, in 1988, Judea Pearl promoted the use of Bayesian Networks as a noise but efficient way of handling uncertain reasoning with his publication of the book Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. [56] and Bayesian methods were used effectively in specialist systems. [57] Even later, in the 1990s, analytical relational learning, an approach that combines likelihood with logical formulas, enabled 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 logic to support were likewise tried. For example, non-monotonic reasoning might be used with reality maintenance systems. A fact upkeep system tracked presumptions and justifications for all inferences. It allowed reasonings to be withdrawn when presumptions were found out to be inaccurate or a contradiction was obtained. Explanations might be offered a reasoning by explaining which rules were applied to produce it and then continuing through underlying reasonings and guidelines all the method back to root assumptions. [58] Lofti Zadeh had actually introduced a various sort of extension to deal with the representation of uncertainty. For instance, in deciding how « heavy » or « tall » a male is, there is regularly no clear « yes » or « no » answer, and a predicate for heavy or tall would rather return values between 0 and 1. Those worths represented to what degree the predicates were real. His fuzzy reasoning even more provided a means for propagating mixes of these worths through rational solutions. [59]
Machine learning
Symbolic device finding out methods were investigated to attend to the understanding acquisition traffic jam. Among the earliest is Meta-DENDRAL. Meta-DENDRAL used a generate-and-test strategy to produce plausible guideline hypotheses to evaluate against spectra. Domain and job understanding minimized the number of candidates checked to a workable size. Feigenbaum described Meta-DENDRAL as
… the culmination of my imagine the early to mid-1960s relating to 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 used layers of knowledge to guide and prune the search. That understanding acted because we spoke with individuals. But how did the people get the knowledge? By taking a look at thousands of spectra. So we desired a program that would take a look at countless spectra and presume the knowledge of mass spectrometry that DENDRAL might utilize to fix specific hypothesis formation issues. We did it. We were even able to publish new understanding of mass spectrometry in the Journal of the American Chemical Society, giving credit only in a footnote that a program, Meta-DENDRAL, in fact did it. We were able to do something that had actually been a dream: to have a computer program developed a new and publishable piece of science. [51]
In contrast to the knowledge-intensive approach of Meta-DENDRAL, Ross Quinlan invented a domain-independent approach to analytical category, decision tree learning, beginning first with ID3 [60] and after that later on extending its abilities to C4.5. [61] The choice trees produced are glass box, interpretable classifiers, with human-interpretable classification guidelines.
Advances were made in comprehending artificial intelligence theory, too. Tom Mitchell introduced version space knowing which describes learning as a search through a space of hypotheses, with upper, more basic, and lower, more particular, boundaries encompassing all viable hypotheses consistent with the examples seen up until now. [62] More formally, Valiant introduced Probably Approximately Correct Learning (PAC Learning), a structure for the mathematical analysis of maker learning. [63]
Symbolic maker discovering incorporated more than learning by example. E.g., John Anderson provided a cognitive design of human knowing where skill practice results in a compilation of guidelines from a declarative format to a procedural format with his ACT-R cognitive architecture. For instance, a student might learn to apply « Supplementary angles are 2 angles whose procedures sum 180 degrees » as numerous various procedural rules. E.g., one rule may say that if X and Y are supplemental and you understand X, then Y will be 180 – X. He called his method « understanding collection ». ACT-R has actually been utilized successfully to model aspects of human cognition, such as finding out and retention. ACT-R is also used in smart tutoring systems, called cognitive tutors, to effectively teach geometry, computer shows, and algebra to school children. [64]
Inductive reasoning programming was another method to finding out that allowed reasoning programs to be manufactured from input-output examples. E.g., Ehud Shapiro’s MIS (Model Inference System) could manufacture Prolog programs from examples. [65] John R. Koza used hereditary algorithms to program synthesis to develop hereditary shows, which he used to synthesize LISP programs. Finally, Zohar Manna and Richard Waldinger provided a more basic method to program synthesis that manufactures a functional program in the course of proving its specs to be appropriate. [66]
As an alternative to reasoning, Roger Schank introduced case-based reasoning (CBR). The CBR approach described in his book, Dynamic Memory, [67] focuses initially on remembering key analytical cases for future use and generalizing them where proper. When faced with a new problem, CBR recovers the most similar previous case and adapts it to the specifics of the current problem. [68] Another option to logic, hereditary algorithms and genetic shows are based on an evolutionary design of knowing, where sets of guidelines are encoded into populations, the guidelines govern the behavior of individuals, and choice of the fittest prunes out sets of inappropriate guidelines over numerous generations. [69]
Symbolic maker knowing was used to finding out ideas, guidelines, heuristics, and problem-solving. Approaches, aside from those above, consist of:
1. Learning from instruction or advice-i.e., taking human direction, postured as recommendations, and figuring out how to operationalize it in specific circumstances. For instance, in a 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 throughout training. When problem-solving fails, querying the expert to either discover a brand-new exemplar for analytical or to find out a brand-new explanation as to precisely why one exemplar is more pertinent than another. For example, the program Protos discovered to diagnose ringing in the ears cases by connecting with an audiologist. [71] 3. Learning by analogy-constructing issue options based on comparable issues seen in the past, and then customizing their services to fit a new scenario or domain. [72] [73] 4. Apprentice learning systems-learning novel options to problems by observing human analytical. Domain understanding discusses why unique solutions are right and how the option can be generalized. LEAP learned how to create VLSI circuits by observing human designers. [74] 5. Learning by discovery-i.e., developing jobs to perform experiments and then gaining from the results. Doug Lenat’s Eurisko, for example, discovered heuristics to beat human players at the Traveller role-playing game for two years in a row. [75] 6. Learning macro-operators-i.e., looking for beneficial macro-operators to be found out from series of fundamental problem-solving actions. Good macro-operators streamline analytical by allowing issues to be solved 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 numerous times by AI scientists between Kahneman’s research study on human thinking and decision making – shown 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 thinking is more apt for deliberative reasoning, planning, and explanation 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 methods
Neuro-symbolic AI efforts to integrate neural and symbolic architectures in a manner that addresses strengths and weaknesses of each, in a complementary fashion, in order to support robust AI capable of reasoning, finding out, and cognitive modeling. As argued by Valiant [77] and lots of others, [78] the reliable building of abundant computational cognitive designs requires the mix of sound symbolic thinking and effective (machine) learning models. Gary Marcus, likewise, argues that: « We can not construct abundant cognitive models in a sufficient, automated method without the triumvirate of hybrid architecture, rich anticipation, and advanced methods for reasoning. », [79] and in specific: « To build a robust, knowledge-driven technique to AI we must have the machinery of symbol-manipulation in our toolkit. Excessive of helpful understanding is abstract to make do without tools that represent and manipulate abstraction, and to date, the only machinery that we understand of that can such abstract understanding reliably is the device of symbol control. » [80]
Henry Kautz, [19] Francesca Rossi, [81] and Bart Selman [82] have also argued for a synthesis. Their arguments are based upon a need to attend to the 2 type of thinking discussed in Daniel Kahneman’s book, Thinking, Fast and Slow. Kahneman explains human thinking as having two components, System 1 and System 2. System 1 is fast, automated, intuitive and unconscious. System 2 is slower, detailed, and explicit. System 1 is the kind used for pattern acknowledgment while System 2 is far better fit for preparation, deduction, and deliberative thinking. In this view, deep learning best designs the first kind of believing while symbolic thinking finest models the 2nd kind and both are needed.
Garcez and Lamb explain research in this location 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 thinking has actually been held every year given 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 integration of the symbolic and connectionist paradigms of AI has actually been pursued by a fairly small research community over the last twenty years and has actually yielded numerous substantial results. Over the last decade, neural symbolic systems have been revealed efficient in overcoming the so-called propositional fixation of neural networks, as McCarthy (1988) put it in reaction to Smolensky (1988 ); see likewise (Hinton, 1990). Neural networks were revealed capable of representing modal and temporal reasonings (d’Avila Garcez and Lamb, 2006) and pieces of first-order logic (Bader, Hitzler, Hölldobler, 2008; d’Avila Garcez, Lamb, Gabbay, 2009). Further, neural-symbolic systems have actually been used to a variety of problems in the areas of bioinformatics, control engineering, software application verification and adaptation, visual intelligence, ontology knowing, and computer system games. [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 technique of numerous neural designs in natural language processing, where words or subword tokens are both the supreme input and output of large language designs. Examples consist of BERT, RoBERTa, and GPT-3.
– Symbolic [Neural] -is exemplified by AlphaGo, where symbolic techniques are used to call neural techniques. In this case the symbolic technique is Monte Carlo tree search and the neural methods discover how to evaluate game positions.
– Neural|Symbolic-uses a neural architecture to analyze affective information as symbols and relationships that are then reasoned about symbolically.
– Neural: Symbolic → Neural-relies on symbolic thinking to produce or identify training information that is consequently learned by a deep knowing design, e.g., to train a neural model for symbolic computation by utilizing a Macsyma-like symbolic mathematics system to produce or label examples.
– Neural _ Symbolic -uses a neural web that is generated from symbolic rules. An example is the Neural Theorem Prover, [85] which constructs a neural network from an AND-OR evidence tree created from understanding base rules and terms. Logic Tensor Networks [86] also fall under this classification.
– Neural [Symbolic] -allows a neural model to directly call a symbolic thinking engine, e.g., to carry out an action or evaluate a state.
Many key research questions stay, such as:
– What is the very best way to incorporate neural and symbolic architectures? [87]- How should symbolic structures be represented within neural networks and drawn out from them?
– How should common-sense knowledge be learned and reasoned about?
– How can abstract understanding that is hard to encode logically be handled?
Techniques and contributions
This section offers a summary of strategies and contributions in an overall context causing lots of other, more comprehensive posts in Wikipedia. Sections on Machine Learning and Uncertain Reasoning are covered previously in the history area.
AI programs languages
The essential AI shows language in the US during the last symbolic AI boom duration was LISP. LISP is the second earliest programming language after FORTRAN and was produced in 1958 by John McCarthy. LISP supplied the very first read-eval-print loop to support rapid program development. Compiled functions could be easily blended with analyzed functions. Program tracing, stepping, and breakpoints were also offered, along with the ability to alter values or functions and continue from breakpoints or errors. It had the first self-hosting compiler, indicating that the compiler itself was initially written in LISP and after that ran interpretively to compile the compiler code.
Other essential developments pioneered by LISP that have infected other shows languages consist of:
Garbage collection
Dynamic typing
Higher-order functions
Recursion
Conditionals
Programs were themselves information structures that other programs could operate on, permitting the simple definition of higher-level languages.
In contrast to the US, in Europe the crucial AI programs language during that same period was Prolog. Prolog provided a built-in shop of truths and provisions that could be queried by a read-eval-print loop. The store could act as a knowledge base and the stipulations might act as rules or a limited type of reasoning. As a subset of first-order reasoning Prolog was based upon Horn stipulations 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 thought about to refer to precisely one item. Backtracking and marriage are built-in to Prolog.
Alain Colmerauer and Philippe Roussel are credited as the creators of Prolog. Prolog is a form of logic shows, which was created by Robert Kowalski. Its history was likewise influenced by Carl Hewitt’s PLANNER, an assertional database with pattern-directed invocation of methods. For more detail see the section on the origins of Prolog in the PLANNER article.
Prolog is also a kind of declarative shows. The logic clauses that explain programs are directly translated to run the programs defined. No specific series of actions is needed, as holds true with necessary programming languages.
Japan championed Prolog for its Fifth Generation Project, meaning to build unique hardware for high efficiency. Similarly, LISP machines were developed to run LISP, but as the second AI boom turned to bust these business might not take on brand-new workstations that might now run LISP or Prolog natively at similar speeds. See the history section for more detail.
Smalltalk was another influential AI shows language. For example, it presented metaclasses and, in addition to Flavors and CommonLoops, influenced the Common Lisp Object System, or (CLOS), that is now part of Common Lisp, the existing 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 offering a run-time meta-object procedure. [88]
For other AI programs languages see this list of programs languages for expert system. Currently, Python, a multi-paradigm shows language, is the most popular programs language, partly due to its substantial plan library that supports data science, natural language processing, and deep knowing. Python includes a read-eval-print loop, practical aspects such as higher-order functions, and object-oriented programs that includes metaclasses.
Search
Search develops in numerous sort of problem fixing, including preparation, restriction satisfaction, and playing games such as checkers, chess, and go. The very 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 clause knowing, and the DPLL algorithm. For adversarial search when playing video games, alpha-beta pruning, branch and bound, and minimax were early contributions.
Knowledge representation and reasoning
Multiple different approaches to represent knowledge and then factor with those representations have been investigated. Below is a quick overview of methods to knowledge representation and automated reasoning.
Knowledge representation
Semantic networks, conceptual graphs, frames, and reasoning are all techniques to modeling understanding such as domain understanding, problem-solving knowledge, and the semantic meaning of language. Ontologies design crucial 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 utilized for any domain while WordNet is a lexical resource that can likewise be considered as an ontology. YAGO incorporates WordNet as part of its ontology, to align facts drawn out 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 classification of ontologies and for spotting inconsistent classification information. OWL is a language used to represent ontologies with description logic. Protégé is an ontology editor that can read in OWL ontologies and then inspect consistency with deductive classifiers such as such as HermiT. [89]
First-order logic is more basic than description logic. The automated theorem provers talked about listed below can prove theorems in first-order logic. Horn provision reasoning is more restricted than first-order logic and is used in logic programs languages such as Prolog. Extensions to first-order logic include temporal reasoning, to manage time; epistemic logic, to factor about agent understanding; modal logic, to manage possibility and need; and probabilistic logics to manage reasoning and probability together.
Automatic theorem showing
Examples of automated theorem provers for first-order reasoning are:
Prover9.
ACL2.
Vampire.
Prover9 can be utilized in conjunction 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 referred to as Nqthm.
Reasoning in knowledge-based systems
Knowledge-based systems have a specific knowledge base, generally of guidelines, to improve reusability throughout domains by separating procedural code and domain understanding. A separate reasoning engine processes guidelines and adds, 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 limited logical representation is used, Horn Clauses. Pattern-matching, particularly unification, is utilized in Prolog.
A more flexible sort of problem-solving takes place when reasoning about what to do next takes place, instead of merely picking among the available actions. This sort of meta-level thinking is utilized in Soar and in the BB1 chalkboard architecture.
Cognitive architectures such as ACT-R might have additional abilities, such as the capability to put together regularly utilized understanding into higher-level pieces.
Commonsense reasoning
Marvin Minsky first proposed frames as a way of translating common visual scenarios, such as a workplace, and Roger Schank extended this concept to scripts for typical routines, such as dining out. Cyc has attempted to record useful sensible knowledge and has « micro-theories » to deal with specific type of domain-specific reasoning.
Qualitative simulation, such as Benjamin Kuipers’s QSIM, [90] estimates human thinking about ignorant physics, such as what takes place when we heat up a liquid in a pot on the stove. We anticipate it to heat and perhaps boil over, despite the fact that we might not know its temperature level, its boiling point, or other details, such as air pressure.
Similarly, Allen’s temporal period algebra is a simplification of thinking about time and Region Connection Calculus is a simplification of thinking about spatial relationships. Both can be fixed with restriction solvers.
Constraints and constraint-based thinking
Constraint solvers carry out a more minimal kind of reasoning than first-order logic. They can simplify sets of spatiotemporal restrictions, such as those for RCC or Temporal Algebra, in addition to resolving other type of puzzle issues, such as Wordle, Sudoku, cryptarithmetic issues, and so on. Constraint logic programming can be utilized to solve scheduling issues, for instance with constraint handling guidelines (CHR).
Automated preparation
The General Problem Solver (GPS) cast planning as problem-solving used means-ends analysis to develop plans. STRIPS took a different method, viewing planning as theorem proving. Graphplan takes a least-commitment technique to preparation, rather than sequentially choosing actions from a preliminary state, working forwards, or a goal state if working in reverse. Satplan is an approach to preparing where a planning issue is lowered to a Boolean satisfiability problem.
Natural language processing
Natural language processing focuses on treating language as information to carry out jobs such as identifying topics without always understanding the desired meaning. Natural language understanding, on the other hand, constructs a meaning representation and uses that for additional processing, such as addressing questions.
Parsing, tokenizing, spelling correction, part-of-speech tagging, noun and verb expression chunking are all elements of natural language processing long handled by symbolic AI, but because improved by deep learning approaches. 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 offered vector representations of files. In the latter case, vector elements are interpretable as concepts called by Wikipedia articles.
New deep learning methods based on Transformer models have actually now eclipsed these earlier symbolic AI methods and obtained modern efficiency in natural language processing. However, Transformer designs are opaque 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 components is nontransparent.
Agents and multi-agent systems
Agents are self-governing systems embedded in an environment they view and act on in some sense. Russell and Norvig’s basic book on expert system is organized to show agent architectures of increasing elegance. [91] The sophistication of representatives varies from easy reactive representatives, to those with a design of the world and automated preparation abilities, potentially a BDI representative, i.e., one with beliefs, desires, and intents – or alternatively a reinforcement 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 knowing for perception. [92]
In contrast, a multi-agent system consists of numerous agents that communicate among themselves with some inter-agent interaction 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 capability to divide work among the representatives and to increase fault tolerance when agents are lost. Research issues consist of how representatives reach consensus, dispersed problem fixing, multi-agent learning, multi-agent preparation, and dispersed restriction optimization.
Controversies occurred from early in symbolic AI, both within the field-e.g., between logicists (the pro-logic « neats ») and non-logicists (the anti-logic « scruffies »)- and between those who welcomed AI however declined symbolic approaches-primarily connectionists-and those outside the field. Critiques from outside of the field were mainly from theorists, on intellectual grounds, but likewise from funding companies, especially throughout the two AI winters.
The Frame Problem: knowledge representation obstacles for first-order reasoning
Limitations were found in utilizing basic first-order logic to factor about dynamic domains. Problems were found both with regards to mentioning the prerequisites for an action to prosper and in offering axioms for what did not alter after an action was carried out.
McCarthy and Hayes presented the Frame Problem in 1969 in the paper, « Some Philosophical Problems from the Standpoint of Expert System. » [93] An easy example occurs in « showing that a person person could enter conversation with another », as an axiom asserting « if a person has a telephone he still has it after searching for a number in the telephone directory » would be required for the reduction to succeed. Similar axioms would be needed for other domain actions to define what did not change.
A similar issue, called the Qualification Problem, happens in trying to specify the prerequisites for an action to prosper. An infinite number of pathological conditions can be imagined, e.g., a banana in a tailpipe might prevent a car from running properly.
McCarthy’s approach to fix the frame issue was circumscription, a kind of non-monotonic logic where deductions could be made from actions that require just define what would alter while not having to explicitly define whatever that would not alter. Other non-monotonic reasonings supplied truth maintenance systems that revised beliefs causing contradictions.
Other methods of managing more open-ended domains consisted of probabilistic reasoning systems and artificial intelligence to discover new principles and guidelines. McCarthy’s Advice Taker can be considered as an inspiration here, as it could include new knowledge supplied by a human in the kind of assertions or rules. For example, speculative symbolic device discovering systems explored the capability to take top-level natural language guidance and to translate it into domain-specific actionable rules.
Similar to the problems in dealing with dynamic domains, common-sense reasoning is likewise hard to capture in official thinking. Examples of sensible thinking include implicit thinking about how people believe or general understanding of everyday events, things, and living animals. This kind of knowledge is considered given and not deemed noteworthy. Common-sense thinking 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 automobiles that do not know not to drive into cones or not to strike pedestrians strolling a bike).
McCarthy saw his Advice Taker as having sensible, but his definition of sensible was different than the one above. [94] He specified a program as having sound judgment « if it immediately deduces for itself an adequately large class of instant consequences of anything it is informed and what it already knows. «
Connectionist AI: philosophical obstacles and sociological disputes
Connectionist approaches include earlier work on neural networks, [95] such as perceptrons; operate in the mid to late 80s, such as Danny Hillis’s Connection Machine and Yann LeCun’s advances in convolutional neural networks; to today’s more advanced approaches, such as Transformers, GANs, and other operate in deep knowing.
Three philosophical positions [96] have been laid out among connectionists:
1. Implementationism-where connectionist architectures carry out the abilities for symbolic processing,
2. Radical connectionism-where symbolic processing is turned down absolutely, and connectionist architectures underlie intelligence and are totally adequate to explain it,
3. Moderate connectionism-where symbolic processing and connectionist architectures are deemed complementary and both are needed for intelligence
Olazaran, in his sociological history of the debates within the neural network neighborhood, described the moderate connectionism view as essentially suitable with existing research study in neuro-symbolic hybrids:
The third and last position I want to take a look at here is what I call the moderate connectionist view, a more eclectic view of the present debate in between connectionism and symbolic AI. One of the researchers who has elaborated this position most clearly is Andy Clark, a philosopher from the School of Cognitive and Computing Sciences of the University of Sussex (Brighton, England). Clark safeguarded hybrid (partly symbolic, partly connectionist) systems. He declared that (at least) two sort of theories are needed in order to study and model 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 processes (such as serial, deductive reasoning, and generative symbol manipulation procedures) the symbolic paradigm uses appropriate models, and not only « approximations » (contrary to what extreme connectionists would declare). [97]
Gary Marcus has actually claimed that the animus in the deep knowing community versus symbolic methods now might be more sociological than philosophical:
To believe that we can just abandon symbol-manipulation is to suspend shock.
And yet, for the most part, that’s how most existing AI proceeds. Hinton and many others have tried tough to banish symbols altogether. The deep learning hope-seemingly grounded not a lot in science, however in a sort of historic grudge-is that intelligent behavior will emerge simply from the confluence of enormous data and deep knowing. Where classical computers and software application solve jobs by specifying sets of symbol-manipulating guidelines devoted to particular tasks, such as modifying a line in a word processor or performing an estimation in a spreadsheet, neural networks typically attempt to solve jobs by analytical approximation and discovering from examples.
According to Marcus, Geoffrey Hinton and his coworkers have been emphatically « anti-symbolic »:
When deep knowing reemerged in 2012, it was with a type of take-no-prisoners mindset that has characterized the majority of the last years. By 2015, his hostility toward all things signs had fully crystallized. 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 learning in among science’s essential journals, Nature. It closed with a direct attack on symbol control, calling not for reconciliation however for straight-out replacement. Later, Hinton informed an event of European Union leaders that investing any additional cash in symbol-manipulating methods was « a big mistake, » comparing it to buying internal combustion engines in the age of electrical automobiles. [98]
Part of these disputes might be because of unclear terms:
Turing award winner Judea Pearl offers a critique of artificial intelligence which, sadly, conflates the terms device knowing and deep learning. Similarly, when Geoffrey Hinton refers to symbolic AI, the connotation of the term tends to be that of specialist systems dispossessed of any ability to discover. Making use of the terminology is in requirement of explanation. Artificial intelligence is not restricted to association rule mining, c.f. the body of work on symbolic ML and relational learning (the distinctions to deep knowing being the choice of representation, localist rational instead of distributed, and the non-use of gradient-based knowing algorithms). Equally, symbolic AI is not practically production rules written by hand. A proper definition of AI concerns knowledge representation and thinking, autonomous multi-agent systems, preparation and argumentation, along with knowing. [99]
Situated robotics: the world as a model
Another critique of symbolic AI is the embodied cognition approach:
The embodied cognition technique claims that it makes no sense to consider the brain separately: cognition occurs within a body, which is embedded in an environment. We need to study the system as a whole; the brain’s working exploits regularities in its environment, consisting of the rest of its body. Under the embodied cognition technique, robotics, vision, and other sensing units end up being central, not peripheral. [100]
Rodney Brooks developed behavior-based robotics, one method to embodied cognition. Nouvelle AI, another name for this method, is considered as an alternative to both symbolic AI and connectionist AI. His technique rejected representations, either symbolic or distributed, as not just unneeded, but as destructive. Instead, he produced the subsumption architecture, a layered architecture for embodied representatives. Each layer achieves a different purpose and needs to work in the real life. For instance, the first robotic he explains in Intelligence Without Representation, has 3 layers. The bottom layer translates sonar sensing units to avoid objects. The middle layer causes the robot to roam around when there are no barriers. The leading layer triggers the robot to go to more remote locations for further expedition. Each layer can momentarily hinder or suppress a lower-level layer. He slammed AI scientists for specifying AI issues for their systems, when: « There is no tidy division between understanding (abstraction) and reasoning in the genuine world. » [101] He called his robotics « Creatures » and each layer was « made up of a fixed-topology network of simple limited state makers. » [102] In the Nouvelle AI approach, « First, it is critically important to check the Creatures we develop in the real life; i.e., in the same world that we people inhabit. It is dreadful to fall under the temptation of testing them in a streamlined world first, even with the best intentions of later moving activity to an unsimplified world. » [103] His focus on real-world testing remained in contrast to « Early operate in AI focused on video games, geometrical problems, symbolic algebra, theorem proving, and other formal systems » [104] and making use of the blocks world in symbolic AI systems such as SHRDLU.
Current views
Each approach-symbolic, connectionist, and behavior-based-has advantages, however has actually been criticized by the other approaches. Symbolic AI has been slammed as disembodied, liable to the qualification problem, and bad in dealing with the perceptual issues where deep learning excels. In turn, connectionist AI has actually been slammed as poorly suited for deliberative detailed problem resolving, incorporating understanding, and managing planning. Finally, Nouvelle AI excels in reactive and real-world robotics domains however has been slammed for problems in integrating learning and knowledge.
Hybrid AIs including several of these techniques are presently viewed as the course forward. [19] [81] [82] Russell and Norvig conclude that:
Overall, Dreyfus saw areas where AI did not have total answers and stated that Al is therefore impossible; we now see numerous of these very same locations undergoing ongoing research and development resulting in increased capability, not impossibility. [100]
Expert system.
Automated planning and scheduling
Automated theorem proving
Belief revision
Case-based reasoning
Cognitive architecture
Cognitive science
Connectionism
Constraint programming
Deep learning
First-order reasoning
GOFAI
History of expert system
Inductive logic shows
Knowledge-based systems
Knowledge representation and reasoning
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 as soon as stated: « This is AI, so we do not care if it’s psychologically genuine ». [4] McCarthy reiterated his position in 2006 at the AI@50 conference where he stated « Expert system is not, by meaning, simulation of human intelligence ». [28] Pamela McCorduck writes that there are « 2 major branches of artificial intelligence: one aimed at producing intelligent behavior despite how it was achieved, and the other focused on modeling intelligent processes discovered in nature, especially human ones. », [29] Stuart Russell and Peter Norvig wrote « Aeronautical engineering texts do not define the objective of their field as making ‘devices that fly so exactly like pigeons that they can deceive even other pigeons.' » [30] Citations
^ Garnelo, Marta; Shanahan, Murray (October 2019). « 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.
^ 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 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 thresholds of knowledge ». 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 expert system? ». 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 big 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 international 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 Learning Apprentice for VLSI Design ». In Kodratoff & Michalski (1990 ), pp. 271-289.
^ Lenat, Douglas. « Chapter 9: The Role of Heuristics in Learning by Discovery: Three Case Studies ». In Michalski, Carbonell & Mitchell (1983 ), pp. 243-306.
^ Korf, Richard E. (1985 ). Learning to Solve Problems by Searching for Macro-Operators. Research Notes in Expert System. Pitman Publishing. ISBN 0-273-08690-1.
^ Valiant 2008.
^ a b Garcez et al. 2015.
^ Marcus 2020, p. 44.
^ Marcus 2020, p. 17.
^ a b Rossi 2022.
^ a b Selman 2022.
^ Garcez & Lamb 2020, p. 2.
^ Garcez et al. 2002.
^ Rocktäschel, Tim; Riedel, Sebastian (2016 ). « Learning Knowledge Base Inference with Neural Theorem Provers ». Proceedings of the 5th Workshop on Automated Knowledge Base Construction. San Diego, CA: Association for Computational Linguistics. pp. 45-50. doi:10.18653/ v1/W16 -1309. Retrieved 2022-08-06.
^ Serafini, Luciano; Garcez, Artur d’Avila (2016 ), Logic Tensor Networks: Deep Learning and Logical Reasoning from Data and Knowledge, arXiv:1606.04422.
^ a b Garcez, Artur d’Avila; Lamb, Luis C.; Gabbay, Dov M. (2009 ). Neural-Symbolic Cognitive Reasoning (1st ed.). Berlin-Heidelberg: Springer. Bibcode:2009 nscr.book … D. doi:10.1007/ 978-3-540-73246-4. ISBN 978-3-540-73245-7. S2CID 14002173.
^ Kiczales, Gregor; Rivieres, Jim des; Bobrow, Daniel G. (1991-07-30). The Art of the Metaobject Protocol (1st ed.). Cambridge, Mass: The MIT Press. ISBN 978-0-262-61074-2.
^ Motik, Boris; Shearer, Rob; Horrocks, Ian (2009-10-28). « Hypertableau Reasoning for Description Logics ». Journal of 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 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 Artificial Intelligence, Connectionist Networks & Beyond (Technical report). Iowa State University Digital Repository, Computer Science 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 Technology. Springer US. pp. 351-388. doi:10.1007/ 978-0-585-29599-2_11.
Howe, J. (November 1994). « Expert System at Edinburgh University: a Viewpoint ». Archived from the original 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 Artificial Intelligence Approach. Vol. III. San Mateo, Calif.: Morgan Kaufman. ISBN 0-934613-09-5. OCLC 893488404.
Kolata, G. (1982 ). « How can computers get common 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 Expert System 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 GOOD SENSE. Symposium on Mechanization of Thought Processes. NATIONAL PHYSICAL LABORATORY, TEDDINGTON, UK. p. 8.
McCarthy, John; Hayes, Patrick (1969 ). « Some Philosophical Problems From the Standpoint of Expert System ». Machine Intelligence 4. B. Meltzer, Donald Michie (eds.): 463-502.
McCorduck, Pamela (2004 ), Machines Who Think (2nd ed.), Natick, Massachusetts: A. K. Peters, ISBN 1-5688-1205-1.
Michalski, Ryszard; Carbonell, Jaime; Mitchell, Tom, eds. (1983 ). Artificial intelligence: an 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 Science 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 original on 26 July 2020. Retrieved 18 November 2019.
Olazaran, Mikel (1993-01-01), « A Sociological History of the Neural Network Controversy », in Yovits, Marshall C. (ed.), Advances in Computers Volume 37, vol. 37, Elsevier, pp. 335-425, doi:10.1016/ S0065-2458( 08 )60408-8, ISBN 9780120121373, 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 ). Expert system: 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 Artificial Intelligence and Further On.