5 - Connectionism and neural networks
Published online by Cambridge University Press: 05 July 2014
By
Summary
Connectionism and neural networks have become a mainstay of artificial intelligence and cognitive science. Nowadays, conferences on neural networks from the perspective of artificial intelligence (or computational intelligence, as some would put it) are held regularly and are usually fairly well attended (such as International Joint Conferences on Neural Networks). At major cognitive science conferences, work based on connectionist models usually occupies a major place. In many engineering conferences and journals, work utilizing neural network models is commonplace. Their popularity and appeal have reached a stable state in a sense. In other words, they have become an integral part of the study and the exploration of intelligence and cognition.
In this chapter, I will first review briefly the history of connectionist models, identifying major ideas and major areas of applications, and then move on to address the issue of symbolic processing in connectionist models; finally, I will expand the discussion to hybrid connectionist models, which incorporate both connectionist and symbolic processing methods.
Keywords
- Type
- Chapter
- Information
- The Cambridge Handbook of Artificial Intelligence , pp. 108 - 127Publisher: Cambridge University PressPrint publication year: 2014
References
. and . (eds.) (1992). Neural Networks for Vision and Image Processing. Cambridge, MA: MIT Press. An early collection of work on neural networks for vision and image processing.Google Scholar
., ., and the (1986). Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. 1: Foundations. Cambridge, MA: MIT Press. Provides an introduction to early classic work in connectionism.Google Scholar
. and . (eds.) (1995). Computational Architectures Integrating Neural and Symbolic Processes: A Perspective on the State of the Art. Norwell, MA: Kluwer Academic Publishers. An anthology of work on connectionist and hybrid connectionist models.Google Scholar
. and . (eds.) (2000). Hybrid Neural Systems. Berlin: Springer. A more recent collection of major work in connectionist and hybrid connectionist models.CrossRefGoogle Scholar
and (1998). The Atomic Components of Thought. Mahwah, NJ: Lawrence Erlbaum Associates.Google Scholar
and (1990). Connectionism and the Mind: An Introduction to Parallel Processing in Networks. Cambridge, MA: Blackwell.Google Scholar
and (eds.) (1992). Neural Networks for Vision and Image Processing. Cambridge, MA: MIT Press.Google Scholar
and (1991). Learning the structure of event sequences, Journal of Experimental Psychology: General 120: 235–53.CrossRefGoogle ScholarPubMed
and (1986). Mind Over Machine: The Power of Human Intuition and Expertise in the Era of the Computer. New York: The Free Press.Google Scholar
and (1988). Connectionism and cognitive architecture: A critical analysis, Cognition 28: 3–71.CrossRefGoogle ScholarPubMed
and (1988). Evaluating an adaptive network model of human learning, Journal of Memory and Language 27: 166–95.CrossRefGoogle Scholar
and (1989). Analogical mapping by constraint satisfaction, Cognitive Science 13: 295–355.CrossRefGoogle Scholar
(2008). Models of categorization, in (ed.), The Cambridge Handbook of Computational Psychology (pp. 267–301). New York: Cambridge University Press.CrossRefGoogle Scholar
, , and (1995). Why there are complementary learning systems in the hippocampus and neocortex: Insights from the successes and failures of connectionist models of learning and memory, Psychological Review 102: 419–57.CrossRefGoogle ScholarPubMed
(1993). Subsymbolic Natural Language Processing: An Integrated Model of Scripts, Lexicon, and Memory. Cambridge, MA: MIT Press.Google Scholar
and (1976). Computer science as empirical inquiry: Symbols and search, Communications of the ACM 19: 113–26.CrossRefGoogle Scholar
, , and (2008). Computational models of episodic memory, in (ed.), The Cambridge Handbook of Computational Psychology (pp. 189–225). New York: Cambridge University Press.CrossRefGoogle Scholar
and (1988). On language and connectionism: Analysis of a parallel distributed processing model of language acquisition, Cognition 23: 73–193.CrossRefGoogle Scholar
, , and (1991). Philosophy and Connectionist Theory. Hillsdale, NJ: Lawrence Erlbaum Associates.Google Scholar
(2008). Computational models of semantic memory, in (ed.), The Cambridge Handbook of Computational Psychology (pp. 226–266). New York: Cambridge University Press.CrossRefGoogle Scholar
, , and the (1986). Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. 1: Foundations. Cambridge, MA: MIT Press.Google Scholar
and (1990). Learning and applying contextual constraints in sentence comprehension, Artificial Intelligence 46: 217–57.CrossRefGoogle Scholar
and (1987). Parallel networks that learn to pronounce English text, Complex Systems 1: 145–68.Google Scholar
and (1993). From simple associations to systematic reasoning: A connectionist representation of rules, variables, and dynamic bindings using temporal synchrony, Behavioral and Brain Sciences 16: 417–94.CrossRefGoogle Scholar
(1988). On the proper treatment of connectionism, Behavioral and Brain Sciences 11: 1–74.CrossRefGoogle Scholar
(1992). On variable binding in connectionist networks. Connection Science 4: 93–124.CrossRefGoogle Scholar
(1994). Integrating Rules and Connectionism for Robust Reasoning. New York: John Wiley and Sons.Google Scholar
(1999). Accounting for the computational basis of consciousness: A connectionist approach, Consciousness and Cognition 8: 529–65.CrossRefGoogle ScholarPubMed
(2002). Duality of the Mind: A Bottom-Up Approach Toward Cognition. Mahwah, NJ: Lawrence Erlbaum Associates.Google Scholar
and (eds.) (1995). Computational Architectures Integrating Neural and Symbolic Processes: A Perspective on the State of the Art. Norwell, MA: Kluwer Academic Publishers.Google Scholar
, , and (2005). The interaction of the explicit and the implicit in skill learning: A dual-process approach, Psychological Review 112: 159–92.CrossRefGoogle ScholarPubMed
and (2006). Accounting for a variety of reasoning data within a cognitive architecture, Journal of Experimental and Theoretical Artificial Intelligence 18: 169–91.CrossRefGoogle Scholar
and (1988). A distributed connectionist production system, Cognitive Science 12: 423–66.CrossRefGoogle Scholar
and (eds.) (1986). Connectionist Models and Their Implications: Readings from Cognitive Science. Norwood, NJ: Ablex.Google Scholar
- 11
- Cited by