Connectionism Theory and Practice [Paperback]

Over the last decade, an emerging form of computational modeling has steadily gained the respect of many researchers as a radically new and promising approach to cognitive science. Known by a number of names, including connectionism, neural networks, and parallel distributed processing (PDP), this method of computation attempts to model the neural processes that are assumed to underlie cognitive functions in human beings. Unlike the digital computation methods used by AI researchers, connectionist models claim to approximate the kind of spontaneous, creative, and somewhat unpredictable behavior of human agents. However, over the last few years, a heated controversy has arisen over the extent to which connectionist models are able to provide successful explanations for higher cognitive processes. A central theme of this book reviews the adequacy of recent attempts to implement higher cognitive processes in connectionist networks. Cognitive scientists, cognitive psychologists, linguists, philosophers, computer scientists, and others exploring this fascinating science will find this book essential reading.

1. Using Coherence Assumptions to Discover the Underlying Causes of the Sensory Input,G.E. Hinton and S. Becker
2. A Deeper Unity: Some Feerabendian Themes in Neurocomputational Form,Paul M. Churchland
3. Towards a Microstructural Account of Human Reasoning,David E. Rumelhart
4. Connectionism without Tears,Mark S. Seidenberg
5. Grammatical Structure and Distributed Representations,Jeffrey L. Elman
6. Structured Representations in Connectionist Systems? Terence Horgan and John Tienson
7. Local Modelling in Phonology,John Goldsmith
8. Connectionism and the Philosophy of Mental Representation,William Ramsey
9. Connectionism and the Computational Neurobiology of Curve Detection,Steven W. Zucker, Allan Dobbins, and Lee Iverson
10. PDP Learnability and Innatel³D