Connectionism

Last updated
A 'second wave' connectionist (ANN) model with a hidden layer Artificial neural network.svg
A 'second wave' connectionist (ANN) model with a hidden layer

Connectionism is the name of an approach to the study of human mental processes and cognition that utilizes mathematical models known as connectionist networks or artificial neural networks. [1] Connectionism has had many 'waves' since its beginnings.

Contents

The first wave appeared 1943 with Warren Sturgis McCulloch and Walter Pitts both focusing on comprehending neural circuitry through a formal and mathematical approach, [2] and Frank Rosenblatt who published the 1958 paper “The Perceptron: A Probabilistic Model For Information Storage and Organization in the Brain” in Psychological Review, while working at the Cornell Aeronautical Laboratory. [3] The first wave ended with the 1969 book about the limitations of the original perceptron idea, written by Marvin Minsky and Seymour Papert, which contributed to discouraging major funding agencies in the US from investing in connectionist research. [4] With a few noteworthy deviations, most connectionist research entered a period of inactivity until the mid-1980s. The term connectionist model was reintroduced in a 1982 paper in the journal Cognitive Science by Jerome Feldman and Dana Ballard.

The second wave blossomed in the late 1980s, following a 1987 book about Parallel Distributed Processing by James L. McClelland, David E. Rumelhart et al., which introduced a couple of improvements to the simple perceptron idea, such as intermediate processors (now known as "hidden layers") alongside input and output units, and used a sigmoid activation function instead of the old 'all-or-nothing' function. Their work built upon that of John Hopfield, who was a key figure investigating the mathematical characteristics of sigmoid activation functions. [3] From the late 1980s to the mid-1990s, connectionism took on an almost revolutionary tone when Schneider, [5] Terence Horgan and Tienson posed the question of whether connectionism represented a fundamental shift in psychology and so-called “good old-fashioned AI,” or GOFAI. [3] Some advantages of the second wave connectionist approach included its applicability to a broad array of functions, structural approximation to biological neurons, low requirements for innate structure, and capacity for graceful degradation. [6] Its disadvantages included the difficulty in deciphering how ANNs process information or account for the compositionality of mental representations, and a resultant difficulty explaining phenomena at a higher level. [7]

The current (third) wave has been marked by advances in deep learning, which have made possible the creation of large language models. [3] The success of deep-learning networks in the past decade has greatly increased the popularity of this approach, but the complexity and scale of such networks has brought with them increased interpretability problems. [8]

Basic principle

The central connectionist principle is that mental phenomena can be described by interconnected networks of simple and often uniform units. The form of the connections and the units can vary from model to model. For example, units in the network could represent neurons and the connections could represent synapses, as in the human brain. This principle has been seen as an alternative to GOFAI and the classical theories of mind based on symbolic computation, but the extent to which the two approaches are compatible has been the subject of much debate since their inception. [8]

Activation function

Internal states of any network change over time due to neurons sending a signal to a succeeding layer of neurons in the case of a feedforward network, or to a previous layer in the case of a recurrent network. Discovery of non-linear activation functions has enabled the second wave of connectionism.

Memory and learning

Neural networks follow two basic principles:

  1. Any mental state can be described as a n-dimensional vector of numeric activation values over neural units in a network.
  2. Memory and learning are created by modifying the 'weights' of the connections between neural units, generally represented as an n×m matrix. The weights are adjusted according to some learning rule or algorithm, such as Hebbian learning. [9]

Most of the variety among the models comes from:

Biological realism

Connectionist work in general does not need to be biologically realistic. [10] [11] [12] [13] [14] [15] [16] One area where connectionist models are thought to be biologically implausible is with respect to error-propagation networks that are needed to support learning, [17] [18] but error propagation can explain some of the biologically-generated electrical activity seen at the scalp in event-related potentials such as the N400 and P600, [19] and this provides some biological support for one of the key assumptions of connectionist learning procedures. Many recurrent connectionist models also incorporate dynamical systems theory. Many researchers, such as the connectionist Paul Smolensky, have argued that connectionist models will evolve toward fully continuous, high-dimensional, non-linear, dynamic systems approaches.

Precursors

Precursors of the connectionist principles can be traced to early work in psychology, such as that of William James. [20] Psychological theories based on knowledge about the human brain were fashionable in the late 19th century. As early as 1869, the neurologist John Hughlings Jackson argued for multi-level, distributed systems. Following from this lead, Herbert Spencer's Principles of Psychology, 3rd edition (1872), and Sigmund Freud's Project for a Scientific Psychology (composed 1895) propounded connectionist or proto-connectionist theories. These tended to be speculative theories. But by the early 20th century, Edward Thorndike was writing about human learning that posited a connectionist type network. [21]

Hopfield networks had precursors in the Ising model due to Wilhelm Lenz (1920) and Ernst Ising (1925), though the Ising model conceived by them did not involve time. Monte Carlo simulations of Ising model required the advent of computers in the 1950s. [22]

The first wave

The first wave begun in 1943 with Warren Sturgis McCulloch and Walter Pitts both focusing on comprehending neural circuitry through a formal and mathematical approach. McCulloch and Pitts showed how neural systems could implement first-order logic: Their classic paper "A Logical Calculus of Ideas Immanent in Nervous Activity" (1943) is important in this development here. They were influenced by the work of Nicolas Rashevsky in the 1930s and symbolic logic in the style of Principia Mathematica . [23] [3]

Hebb contributed greatly to speculations about neural functioning, and proposed a learning principle, Hebbian learning. Lashley argued for distributed representations as a result of his failure to find anything like a localized engram in years of lesion experiments. Friedrich Hayek independently conceived the model, first in a brief unpublished manuscript in 1920, [24] [25] then expanded into a book in 1952. [26]

The Perceptron machines were proposed and built by Frank Rosenblatt, who published the 1958 paper “The Perceptron: A Probabilistic Model For Information Storage and Organization in the Brain” in Psychological Review, while working at the Cornell Aeronautical Laboratory. He cited Hebb, Hayek, Uttley, and Ashby as main influences.

Another form of connectionist model was the relational network framework developed by the linguist Sydney Lamb in the 1960s.

The research group led by Widrow empirically searched for methods to train two-layered ADALINE networks (MADALINE), with limited success. [27] [28]

A method to train multilayered perceptrons with arbitrary levels of trainable weights was published by Alexey Grigorevich Ivakhnenko and Valentin Lapa in 1965, called the Group Method of Data Handling. This method employs incremental layer by layer training based on regression analysis, where useless units in hidden layers are pruned with the help of a validation set. [29] [30] [31]

The first multilayered perceptrons trained by stochastic gradient descent [32] was published in 1967 by Shun'ichi Amari. [33] In computer experiments conducted by Amari's student Saito, a five layer MLP with two modifiable layers learned useful internal representations to classify non-linearily separable pattern classes. [30]

In 1972, Shun'ichi Amari produced an early example of self-organizing network. [34]

The neural network winter

There was some conflict among artificial intelligence researchers as to what neural networks are useful for. Around late 1960s, there was a widespread lull in research and publications on neural networks, "the neural network winter", which lasted through the 1970s, during which the field of artificial intelligence turned towards symbolic methods. The publication of Perceptrons (1969) is typically regarded as a catalyst of this event. [35] [36]

The second wave

The second wave begun in the early 1980s. Some key publications included (John Hopfield, 1982) [37] which popularized Hopfield networks, the 1986 paper that popularized backpropagation, [38] and the 1987 two-volume book about the Parallel Distributed Processing (PDP) by James L. McClelland, David E. Rumelhart et al., which has introduced a couple of improvements to the simple perceptron idea, such as intermediate processors (known as "hidden layers" now) alongside input and output units and using sigmoid activation function instead of the old 'all-or-nothing' function.

Hopfield approached the field from the perspective of statistical mechanics, providing some early forms of mathematical rigor that increased the perceived respectability of the field. [3] Another important series of publications proved that neural networks are universal function approximators, which also provided some mathematical respectability. [39]

Some early popular demonstration projects appeared during this time. NETtalk (1987) learned to pronounce written English. It achieved popular success, appearing on the Today show. [40] TD-Gammon (1992) reached top human level in backgammon. [41]

Connectionism vs. computationalism debate

As connectionism became increasingly popular in the late 1980s, some researchers (including Jerry Fodor, Steven Pinker and others) reacted against it. They argued that connectionism, as then developing, threatened to obliterate what they saw as the progress being made in the fields of cognitive science and psychology by the classical approach of computationalism. Computationalism is a specific form of cognitivism that argues that mental activity is computational, that is, that the mind operates by performing purely formal operations on symbols, like a Turing machine. Some researchers argued that the trend in connectionism represented a reversion toward associationism and the abandonment of the idea of a language of thought, something they saw as mistaken. In contrast, those very tendencies made connectionism attractive for other researchers.

Connectionism and computationalism need not be at odds, but the debate in the late 1980s and early 1990s led to opposition between the two approaches. Throughout the debate, some researchers have argued that connectionism and computationalism are fully compatible, though full consensus on this issue has not been reached. Differences between the two approaches include the following:

Despite these differences, some theorists have proposed that the connectionist architecture is simply the manner in which organic brains happen to implement the symbol-manipulation system. This is logically possible, as it is well known that connectionist models can implement symbol-manipulation systems of the kind used in computationalist models, [42] as indeed they must be able if they are to explain the human ability to perform symbol-manipulation tasks. Several cognitive models combining both symbol-manipulative and connectionist architectures have been proposed. Among them are Paul Smolensky's Integrated Connectionist/Symbolic Cognitive Architecture (ICS). [8] [43] and Ron Sun's CLARION (cognitive architecture). But the debate rests on whether this symbol manipulation forms the foundation of cognition in general, so this is not a potential vindication of computationalism. Nonetheless, computational descriptions may be helpful high-level descriptions of cognition of logic, for example.

The debate was largely centred on logical arguments about whether connectionist networks could produce the syntactic structure observed in this sort of reasoning. This was later achieved although using fast-variable binding abilities outside of those standardly assumed in connectionist models. [42] [44]

Part of the appeal of computational descriptions is that they are relatively easy to interpret, and thus may be seen as contributing to our understanding of particular mental processes, whereas connectionist models are in general more opaque, to the extent that they may be describable only in very general terms (such as specifying the learning algorithm, the number of units, etc.), or in unhelpfully low-level terms. In this sense, connectionist models may instantiate, and thereby provide evidence for, a broad theory of cognition (i.e., connectionism), without representing a helpful theory of the particular process that is being modelled. In this sense, the debate might be considered as to some extent reflecting a mere difference in the level of analysis in which particular theories are framed. Some researchers suggest that the analysis gap is the consequence of connectionist mechanisms giving rise to emergent phenomena that may be describable in computational terms. [45]

In the 2000s, the popularity of dynamical systems in philosophy of mind have added a new perspective on the debate; [46] [47] some authors[ which? ] now argue that any split between connectionism and computationalism is more conclusively characterized as a split between computationalism and dynamical systems.

In 2014, Alex Graves and others from DeepMind published a series of papers describing a novel Deep Neural Network structure called the Neural Turing Machine [48] able to read symbols on a tape and store symbols in memory. Relational Networks, another Deep Network module published by DeepMind, are able to create object-like representations and manipulate them to answer complex questions. Relational Networks and Neural Turing Machines are further evidence that connectionism and computationalism need not be at odds.

Symbolism vs. connectionism debate

Smolensky's Subsymbolic Paradigm [49] [50] has to meet the Fodor-Pylyshyn challenge [51] [52] [53] [54] formulated by classical symbol theory for a convincing theory of cognition in modern connectionism. In order to be an adequate alternative theory of cognition, Smolensky's Subsymbolic Paradigm would have to explain the existence of systematicity or systematic relations in language cognition without the assumption that cognitive processes are causally sensitive to the classical constituent structure of mental representations. The subsymbolic paradigm, or connectionism in general, would thus have to explain the existence of systematicity and compositionality without relying on the mere implementation of a classical cognitive architecture. This challenge implies a dilemma: If the Subsymbolic Paradigm could contribute nothing to the systematicity and compositionality of mental representations, it would be insufficient as a basis for an alternative theory of cognition. However, if the Subsymbolic Paradigm's contribution to systematicity requires mental processes grounded in the classical constituent structure of mental representations, the theory of cognition it develops would be, at best, an implementation architecture of the classical model of symbol theory and thus not a genuine alternative (connectionist) theory of cognition. [55] The classical model of symbolism is characterized by (1) a combinatorial syntax and semantics of mental representations and (2) mental operations as structure-sensitive processes, based on the fundamental principle of syntactic and semantic constituent structure of mental representations as used in Fodor's "Language of Thought (LOT)". [56] [57] This can be used to explain the following closely related properties of human cognition, namely its (1) productivity, (2) systematicity, (3) compositionality, and (4) inferential coherence. [58]

This challenge has been met in modern connectionism, for example, not only by Smolensky's "Integrated Connectionist/Symbolic (ICS) Cognitive Architecture", [59] [60] but also by Werning and Maye's "Oscillatory Networks". [61] [62] [63] An overview of this is given for example by Bechtel & Abrahamsen, [64] Marcus [65] and Maurer. [66]

See also

Notes

  1. ↑ "Internet Encyclopedia of Philosophy". iep.utm.edu. Retrieved 2023-08-19.
  2. ↑ McCulloch, Warren S.; Pitts, Walter (1943-12-01). "A logical calculus of the ideas immanent in nervous activity". The Bulletin of Mathematical Biophysics. 5 (4): 115–133. doi:10.1007/BF02478259. ISSN   1522-9602.
  3. 1 2 3 4 5 6 Berkeley, Istvan S. N. (2019). "The Curious Case of Connectionism". Open Philosophy. 2019 (2): 190–205. doi: 10.1515/opphil-2019-0018 . S2CID   201061823.
  4. ↑ Boden, Margaret (2006). Mind as Machine: A History of Cognitive Science . Oxford: Oxford U.P. p. 914. ISBN   978-0-262-63268-3.
  5. ↑ Schneider, Walter (1987). "Connectionism: Is it a Paradigm Shift for Psychology?". Behavior Research Methods, Instruments, & Computers. 19: 73–83. doi: 10.1515/opphil-2019-0018 . S2CID   201061823.
  6. ↑ Marcus, Gary F. (2001). The Algebraic Mind: Integrating Connectionism and Cognitive Science (Learning, Development, and Conceptual Change) . Cambridge, Massachusetts: MIT Press. pp.  27–28. ISBN   978-0-262-63268-3.
  7. ↑ Smolensky, Paul (1999). "Grammar-based Connectionist Approaches to Language". Cognitive Science. 23 (4): 589–613. doi: 10.1207/s15516709cog2304_9 .
  8. 1 2 3 Garson, James (27 November 2018). Zalta, Edward N. (ed.). The Stanford Encyclopedia of Philosophy. Metaphysics Research Lab, Stanford University – via Stanford Encyclopedia of Philosophy.
  9. ↑ Novo, María-Luisa; Alsina, Ángel; Marbán, José-María; Berciano, Ainhoa (2017). "Connective Intelligence for Childhood Mathematics Education". Comunicar (in Spanish). 25 (52): 29–39. doi: 10.3916/c52-2017-03 . hdl: 10272/14085 . ISSN   1134-3478.
  10. ↑ "Encephalos Journal". www.encephalos.gr. Retrieved 2018-02-20.
  11. ↑ Wilson, Elizabeth A. (2016-02-04). Neural Geographies: Feminism and the Microstructure of Cognition. Routledge. ISBN   978-1-317-95876-5.
  12. ↑ Di Paolo, E.A (1 January 2003). "Organismically-inspired robotics: homeostatic adaptation and teleology beyond the closed sensorimotor loop" (PDF). Dynamical Systems Approach to Embodiment and Sociality, Advanced Knowledge International. University of Sussex. S2CID   15349751 . Retrieved 29 December 2023.
  13. ↑ Zorzi, Marco; Testolin, Alberto; Stoianov, Ivilin P. (2013-08-20). "Modeling language and cognition with deep unsupervised learning: a tutorial overview". Frontiers in Psychology. 4: 515. doi: 10.3389/fpsyg.2013.00515 . ISSN   1664-1078. PMC   3747356 . PMID   23970869.
  14. ↑ Tieszen, R. (2011). "Analytic and Continental Philosophy, Science, and Global Philosophy". Comparative Philosophy. 2 (2): 4–22. Retrieved 29 December 2023.
  15. ↑ Browne, A. (1997-01-01). Neural Network Perspectives on Cognition and Adaptive Robotics. CRC Press. ISBN   978-0-7503-0455-9.
  16. ↑ Pfeifer, R.; Schreter, Z.; Fogelman-Soulié, F.; Steels, L. (1989-08-23). Connectionism in Perspective. Elsevier. ISBN   978-0-444-59876-9.
  17. ↑ Crick, Francis (January 1989). "The recent excitement about neural networks". Nature. 337 (6203): 129–132. Bibcode:1989Natur.337..129C. doi:10.1038/337129a0. ISSN   1476-4687. PMID   2911347. S2CID   5892527.
  18. ↑ Rumelhart, David E.; Hinton, Geoffrey E.; Williams, Ronald J. (October 1986). "Learning representations by back-propagating errors". Nature. 323 (6088): 533–536. Bibcode:1986Natur.323..533R. doi:10.1038/323533a0. ISSN   1476-4687. S2CID   205001834.
  19. ↑ Fitz, Hartmut; Chang, Franklin (2019-06-01). "Language ERPs reflect learning through prediction error propagation". Cognitive Psychology. 111: 15–52. doi:10.1016/j.cogpsych.2019.03.002. hdl: 21.11116/0000-0003-474F-6 . ISSN   0010-0285. PMID   30921626. S2CID   85501792.
  20. ↑ Anderson, James A.; Rosenfeld, Edward (1989). "Chapter 1: (1890) William James Psychology (Brief Course)". Neurocomputing: Foundations of Research. A Bradford Book. p. 1. ISBN   978-0-262-51048-6.
  21. ↑ Edward Thorndike (1931) Human Learning, page 122
  22. ↑ Brush, Stephen G. (1967). "History of the Lenz-Ising Model". Reviews of Modern Physics. 39 (4): 883–893. Bibcode:1967RvMP...39..883B. doi:10.1103/RevModPhys.39.883.
  23. ↑ McCulloch, Warren S.; Pitts, Walter (1943-12-01). "A logical calculus of the ideas immanent in nervous activity". The Bulletin of Mathematical Biophysics. 5 (4): 115–133. doi:10.1007/BF02478259. ISSN   1522-9602.
  24. ↑ Hayek, Friedrich A. [1920] 1991. Beiträge zur Theorie der Entwicklung des Bewusstseins [Contributions to a theory of how consciousness develops]. Manuscript, translated by Grete Heinz.
  25. ↑ Caldwell, Bruce (2004). "Some Reflections on F.A. Hayek's The Sensory Order". Journal of Bioeconomics. 6 (3): 239–254. doi:10.1007/s10818-004-5505-9. ISSN   1387-6996. S2CID   144437624.
  26. ↑ Hayek, F. A. (2012-09-15). The Sensory Order: An Inquiry into the Foundations of Theoretical Psychology (1st ed.). The University of Chicago Press.
  27. ↑ pp 124-129, Olazaran Rodriguez, Jose Miguel. A historical sociology of neural network research . PhD Dissertation. University of Edinburgh, 1991.
  28. ↑ Widrow, B. (1962) Generalization and information storage in networks of ADALINE "neurons". In M. C. Yovits, G. T. Jacobi, & G. D. Goldstein (Ed.), Self-Organizing Svstems-1962 (pp. 435-461). Washington, DC: Spartan Books.
  29. ↑ Ivakhnenko, A. G.; Grigorʹevich Lapa, Valentin (1967). Cybernetics and forecasting techniques. American Elsevier Pub. Co.
  30. 1 2 Schmidhuber, Jürgen (2022). "Annotated History of Modern AI and Deep Learning". arXiv: 2212.11279 [cs.NE].
  31. ↑ Ivakhnenko, A. G. (1973). Cybernetic Predicting Devices. CCM Information Corporation.
  32. ↑ Robbins, H.; Monro, S. (1951). "A Stochastic Approximation Method". The Annals of Mathematical Statistics. 22 (3): 400. doi: 10.1214/aoms/1177729586 .
  33. ↑ Amari, Shun'ichi (1967). "A theory of adaptive pattern classifier". IEEE Transactions. EC (16): 279–307.
  34. ↑ Amari, S.-I. (November 1972). "Learning Patterns and Pattern Sequences by Self-Organizing Nets of Threshold Elements". IEEE Transactions on Computers. C-21 (11): 1197–1206. doi:10.1109/T-C.1972.223477. ISSN   0018-9340.
  35. ↑ 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   978-0-12-012137-3 , retrieved 2024-08-07
  36. ↑ Olazaran, Mikel (August 1996). "A Sociological Study of the Official History of the Perceptrons Controversy". Social Studies of Science. 26 (3): 611–659. doi:10.1177/030631296026003005. ISSN   0306-3127.
  37. ↑ Hopfield, J J (April 1982). "Neural networks and physical systems with emergent collective computational abilities". Proceedings of the National Academy of Sciences. 79 (8): 2554–2558. Bibcode:1982PNAS...79.2554H. doi: 10.1073/pnas.79.8.2554 . ISSN   0027-8424. PMC   346238 . PMID   6953413.
  38. ↑ Rumelhart, David E.; Hinton, Geoffrey E.; Williams, Ronald J. (October 1986). "Learning representations by back-propagating errors". Nature. 323 (6088): 533–536. Bibcode:1986Natur.323..533R. doi:10.1038/323533a0. ISSN   1476-4687.
  39. ↑ Cybenko, G. (1989-12-01). "Approximation by superpositions of a sigmoidal function". Mathematics of Control, Signals and Systems. 2 (4): 303–314. Bibcode:1989MCSS....2..303C. doi:10.1007/BF02551274. ISSN   1435-568X.
  40. ↑ Sejnowski, Terrence J. (2018). The deep learning revolution. Cambridge, Massachusetts London, England: The MIT Press. ISBN   978-0-262-03803-4.
  41. ↑ Sammut, Claude; Webb, Geoffrey I., eds. (2010), "TD-Gammon", Encyclopedia of Machine Learning, Boston, MA: Springer US, pp. 955–956, doi:10.1007/978-0-387-30164-8_813, ISBN   978-0-387-30164-8 , retrieved 2023-12-25
  42. 1 2 Chang, Franklin (2002). "Symbolically speaking: a connectionist model of sentence production". Cognitive Science. 26 (5): 609–651. doi: 10.1207/s15516709cog2605_3 . ISSN   1551-6709.
  43. ↑ Smolensky, Paul (1990). "Tensor Product Variable Binding and the Representation of Symbolic Structures in Connectionist Systems" (PDF). Artificial Intelligence. 46 (1–2): 159–216. doi:10.1016/0004-3702(90)90007-M.
  44. ↑ Shastri, Lokendra; Ajjanagadde, Venkat (September 1993). "From simple associations to systematic reasoning: A connectionist representation of rules, variables and dynamic bindings using temporal synchrony". Behavioral and Brain Sciences. 16 (3): 417–451. doi:10.1017/S0140525X00030910. ISSN   1469-1825. S2CID   14973656.
  45. ↑ Ellis, Nick C. (1998). "Emergentism, Connectionism and Language Learning" (PDF). Language Learning. 48 (4): 631–664. doi:10.1111/0023-8333.00063.
  46. ↑ Van Gelder, Tim (1998), "The dynamical hypothesis in cognitive science", Behavioral and Brain Sciences, 21 (5): 615–28, discussion 629–65, doi:10.1017/S0140525X98001733, PMID   10097022 , retrieved 28 May 2022
  47. ↑ Beer, Randall D. (March 2000). "Dynamical approaches to cognitive science". Trends in Cognitive Sciences. 4 (3): 91–99. doi:10.1016/s1364-6613(99)01440-0. ISSN   1364-6613. PMID   10689343. S2CID   16515284.
  48. ↑ Graves, Alex (2014). "Neural Turing Machines". arXiv: 1410.5401 [cs.NE].
  49. ↑ P. Smolensky: On the proper treatment of connectionism. In: Behavioral and Brain Sciences. Band 11, 1988, S. 1-74.
  50. ↑ P. Smolensky: The constituent structure of connectionist mental states: a reply to Fodor and Pylyshyn. In: T. Horgan, J. Tienson (Hrsg.): Spindel Conference 1987: Connectionism and the Philosophy of Mind. The Southern Journal of Philosophy. Special Issue on Connectionism and the Foundations of Cognitive Science. Supplement. Band 26, 1988, S. 137-161.
  51. ↑ J.A. Fodor, Z.W. Pylyshyn: Connectionism and cognitive architecture: a critical analysis. Cognition. Band 28, 1988, S. 12-13, 33-50.
  52. ↑ J.A. Fodor, B. McLaughlin: Connectionism and the problem of systematicity: why Smolensky's solution doesn't work. Cognition. Band 35, 1990, S. 183-184.
  53. ↑ B. McLaughlin: The connectionism/classicism battle to win souls. Philosophical Studies, Band 71, 1993, S. 171-172.
  54. ↑ B. McLaughlin: Can an ICS architecture meet the systematicity and productivity challenges? In: P. Calvo, J. Symons (Hrsg.): The Architecture of Cognition. Rethinking Fodor and Pylyshyn's Systematicity Challenge. MIT Press, Cambridge/MA, London, 2014, S. 31-76.
  55. ↑ J.A. Fodor, B. McLaughlin: Connectionism and the problem of systematicity: Why Smolensky's solution doesn't work. Cognition. Band 35, 1990, S. 183-184.
  56. ↑ J.A. Fodor: The language of thought. Harvester Press, Sussex, 1976, ISBN 0-85527-309-7.
  57. ↑ J.A. Fodor: LOT 2: The language of thought revisited. Clarendon Press, Oxford, 2008, ISBN 0-19-954877-3.
  58. ↑ J.A. Fodor, Z.W. Pylyshyn (1988), S. 33-48.
  59. ↑ P. Smolenky: Reply: Constituent structure and explanation in an integrated connectionist / symbolic cognitive architecture. In: C. MacDonald, G. MacDonald (Hrsg.): Connectionism: Debates on psychological explanation. Blackwell Publishers. Oxford/UK, Cambridge/MA. Vol. 2, 1995, S. 224, 236-239, 242-244, 250-252, 282.
  60. ↑ P. Smolensky, G. Legendre: The Harmonic Mind: From Neural Computation to Optimality-Theoretic Grammar. Vol. 1: Cognitive Architecture. A Bradford Book, The MIT Press, Cambridge, London, 2006a, ISBN 0-262-19526-7, S. 65-67, 69-71, 74-75, 154-155, 159-202, 209-210, 235-267, 271-342, 513.
  61. ↑ M. Werning: Neuronal synchronization, covariation, and compositional representation. In: M. Werning, E. Machery, G. Schurz (Hrsg.): The compositionality of meaning and content. Vol. II: Applications to linguistics, psychology and neuroscience. Ontos Verlag, 2005, S. 283-312.
  62. ↑ M. Werning: Non-symbolic compositional representation and its neuronal foundation: towards an emulative semantics. In: M. Werning, W. Hinzen, E. Machery (Hrsg.): The Oxford Handbook of Compositionality. Oxford University Press, 2012, S. 633-654.
  63. ↑ A. Maye und M. Werning: Neuronal synchronization: from dynamics feature binding to compositional representations. Chaos and Complexity Letters, Band 2, S. 315-325.
  64. ↑ Bechtel, W., Abrahamsen, A.A. Connectionism and the Mind: Parallel Processing, Dynamics, and Evolution in Networks. 2nd Edition. Blackwell Publishers, Oxford. 2002
  65. ↑ G.F. Marcus: The algebraic mind. Integrating connectionism and cognitive science. Bradford Book, The MIT Press, Cambridge, 2001, ISBN 0-262-13379-2.
  66. ↑ H. Maurer: Cognitive science: Integrative synchronization mechanisms in cognitive neuroarchitectures of the modern connectionism. CRC Press, Boca Raton/FL, 2021, ISBN 978-1-351-04352-6. https://doi.org/10.1201/9781351043526

Related Research Articles

<span class="mw-page-title-main">Cognitive science</span> Interdisciplinary scientific study of cognitive processes

Cognitive science is the interdisciplinary, scientific study of the mind and its processes. It examines the nature, the tasks, and the functions of cognition. Mental faculties of concern to cognitive scientists include language, perception, memory, attention, reasoning, and emotion; to understand these faculties, cognitive scientists borrow from fields such as linguistics, psychology, artificial intelligence, philosophy, neuroscience, and anthropology. The typical analysis of cognitive science spans many levels of organization, from learning and decision to logic and planning; from neural circuitry to modular brain organization. One of the fundamental concepts of cognitive science is that "thinking can best be understood in terms of representational structures in the mind and computational procedures that operate on those structures."

In artificial intelligence, symbolic artificial intelligence is the term for the collection of all methods in artificial intelligence research that are based on high-level symbolic (human-readable) representations of problems, logic and search. Symbolic AI used tools such as logic programming, production rules, semantic nets and frames, and it developed applications such as knowledge-based systems, symbolic mathematics, automated theorem provers, ontologies, the semantic web, and automated planning and scheduling systems. The Symbolic AI paradigm led to seminal ideas in search, symbolic programming languages, agents, multi-agent systems, the semantic web, and the strengths and limitations of formal knowledge and reasoning systems.

A cognitive model is a representation of one or more cognitive processes in humans or other animals for the purposes of comprehension and prediction. There are many types of cognitive models, and they can range from box-and-arrow diagrams to a set of equations to software programs that interact with the same tools that humans use to complete tasks. In terms of information processing, cognitive modeling is modeling of human perception, reasoning, memory and action.

<span class="mw-page-title-main">Jerry Fodor</span> American philosopher (1935–2017)

Jerry Alan Fodor was an American philosopher and the author of many crucial works in the fields of philosophy of mind and cognitive science. His writings in these fields laid the groundwork for the modularity of mind and the language of thought hypotheses, and he is recognized as having had "an enormous influence on virtually every portion of the philosophy of mind literature since 1960." At the time of his death in 2017, he held the position of State of New Jersey Professor of Philosophy, Emeritus, at Rutgers University, and had taught previously at the City University of New York Graduate Center and MIT.

The language of thought hypothesis (LOTH), sometimes known as thought ordered mental expression (TOME), is a view in linguistics, philosophy of mind and cognitive science, forwarded by American philosopher Jerry Fodor. It describes the nature of thought as possessing "language-like" or compositional structure. On this view, simple concepts combine in systematic ways to build thoughts. In its most basic form, the theory states that thought, like language, has syntax.

<span class="mw-page-title-main">Dynamical systems theory</span> Area of mathematics used to describe the behavior of complex dynamical systems

Dynamical systems theory is an area of mathematics used to describe the behavior of complex dynamical systems, usually by employing differential equations or difference equations. When differential equations are employed, the theory is called continuous dynamical systems. From a physical point of view, continuous dynamical systems is a generalization of classical mechanics, a generalization where the equations of motion are postulated directly and are not constrained to be Euler–Lagrange equations of a least action principle. When difference equations are employed, the theory is called discrete dynamical systems. When the time variable runs over a set that is discrete over some intervals and continuous over other intervals or is any arbitrary time-set such as a Cantor set, one gets dynamic equations on time scales. Some situations may also be modeled by mixed operators, such as differential-difference equations.

Paul Smolensky is Krieger-Eisenhower Professor of Cognitive Science at the Johns Hopkins University and a Senior Principal Researcher at Microsoft Research, Redmond Washington.

<span class="mw-page-title-main">James McClelland (psychologist)</span>

James Lloyd "Jay" McClelland, FBA is the Lucie Stern Professor at Stanford University, where he was formerly the chair of the Psychology Department. He is best known for his work on statistical learning and Parallel Distributed Processing, applying connectionist models to explain cognitive phenomena such as spoken word recognition and visual word recognition. McClelland is to a large extent responsible for the large increase in scientific interest in connectionism in the 1980s.

A cognitive architecture refers to both a theory about the structure of the human mind and to a computational instantiation of such a theory used in the fields of artificial intelligence (AI) and computational cognitive science. These formalized models can be used to further refine comprehensive theories of cognition and serve as the frameworks for useful artificial intelligence programs. Successful cognitive architectures include ACT-R and SOAR. The research on cognitive architectures as software instantiation of cognitive theories was initiated by Allen Newell in 1990.

<span class="mw-page-title-main">Neural network (biology)</span> Structure in nervous systems

A neural network, also called a neuronal network, is an interconnected population of neurons. Biological neural networks are studied to understand the organization and functioning of nervous systems.

Computational cognition is the study of the computational basis of learning and inference by mathematical modeling, computer simulation, and behavioral experiments. In psychology, it is an approach which develops computational models based on experimental results. It seeks to understand the basis behind the human method of processing of information. Early on computational cognitive scientists sought to bring back and create a scientific form of Brentano's psychology.

Mathematical psychology is an approach to psychological research that is based on mathematical modeling of perceptual, thought, cognitive and motor processes, and on the establishment of law-like rules that relate quantifiable stimulus characteristics with quantifiable behavior. The mathematical approach is used with the goal of deriving hypotheses that are more exact and thus yield stricter empirical validations. There are five major research areas in mathematical psychology: learning and memory, perception and psychophysics, choice and decision-making, language and thinking, and measurement and scaling.

Neurophilosophy or the philosophy of neuroscience is the interdisciplinary study of neuroscience and philosophy that explores the relevance of neuroscientific studies to the arguments traditionally categorized as philosophy of mind. The philosophy of neuroscience attempts to clarify neuroscientific methods and results using the conceptual rigor and methods of philosophy of science.

<span class="mw-page-title-main">David Rumelhart</span> American psychologist (1942–2011)

David Everett Rumelhart was an American psychologist who made many contributions to the formal analysis of human cognition, working primarily within the frameworks of mathematical psychology, symbolic artificial intelligence, and parallel distributed processing. He also admired formal linguistic approaches to cognition, and explored the possibility of formulating a formal grammar to capture the structure of stories.

Neural computation is the information processing performed by networks of neurons. Neural computation is affiliated with the philosophical tradition known as Computational theory of mind, also referred to as computationalism, which advances the thesis that neural computation explains cognition. The first persons to propose an account of neural activity as being computational was Warren McCullock and Walter Pitts in their seminal 1943 paper, A Logical Calculus of the Ideas Immanent in Nervous Activity.

The term hybrid neural network can have two meanings:

  1. Biological neural networks interacting with artificial neuronal models, and
  2. Artificial neural networks with a symbolic part.

In philosophy of mind, the computational theory of mind (CTM), also known as computationalism, is a family of views that hold that the human mind is an information processing system and that cognition and consciousness together are a form of computation. It is closely related to functionalism, a broader theory that defines mental states by what they do rather than what they're made of.

Ron Sun is a cognitive scientist who has made significant contributions to computational psychology and other areas of cognitive science and artificial intelligence. He is currently professor of cognitive sciences at Rensselaer Polytechnic Institute, and formerly the James C. Dowell Professor of Engineering and Professor of Computer Science at University of Missouri. He received his Ph.D. in 1992 from Brandeis University.

Harmonic grammar is a linguistic model proposed by Geraldine Legendre, Yoshiro Miyata, and Paul Smolensky in 1990. It is a connectionist approach to modeling linguistic well-formedness. During the late 2000s and early 2010s, the term 'harmonic grammar' has been used to refer more generally to models of language that use weighted constraints, including ones that are not explicitly connectionist – see e.g. Pater (2009) and Potts et al. (2010).

In the philosophy of artificial intelligence, GOFAI is classical symbolic AI, as opposed to other approaches, such as neural networks, situated robotics, narrow symbolic AI or neuro-symbolic AI. The term was coined by philosopher John Haugeland in his 1985 book Artificial Intelligence: The Very Idea.

References

Listen to this article (19 minutes)
Sound-icon.svg
This audio file was created from a revision of this article dated 26 November 2011 (2011-11-26), and does not reflect subsequent edits.
(Audio help  · More spoken articles)
This page is based on this Wikipedia article
Text is available under the CC BY-SA 4.0 license; additional terms may apply.
Images, videos and audio are available under their respective licenses.