Connectionism : a hands-on approach / Michael R.W. Dawson.

Includes bibliographical references (pages 188-194) and indexes.

Ch. 1. Hands-on connectionism -- Ch. 2. The distributed associative memory -- Ch. 3. The James program -- Ch. 4. Introducing Hebb learning -- Ch. 5. Limitations of Hebb learning -- Ch. 6. Introducing the delta rule -- Ch. 7. Distributed networks and human memory -- Ch. 8. Limitations of delta rule learning -- Ch. 9. The perceptron -- Ch. 10. The Rosenblatt program -- Ch. 11. Perceptrons and logic gates -- Ch. 12. Performing more logic with perceptrons -- Ch. 13. Value units and linear nonseparability -- Ch. 14. Network by problem type interactions -- Ch. 15. Perceptrons and generalization -- Ch. 16. Animal learning theory and perceptrons -- Ch. 17. The multilayer perceptron -- Ch. 18. The Rumelhart program -- Ch. 19. Beyond the perceptron's limits -- Ch. 20. Symmetry as a second case study -- Ch. 21. How many hidden units? -- Ch. 22. Scaling up with the parity problem -- Ch. 23. Selectionism and parity -- Ch. 24. Interpreting a small network.

Ch. 25. Interpreting networks of value units -- Ch. 26. Interpreting distributed representations -- Ch. 27. Creating your own training sets.

CONNNECTIONISM is a'hands on' introduction to connectionist modeling. Three different types of connectionist architectures - distributed associative memory, perceptron, and multilayer perceptron - are explored. In an accessible style, Dawson provides a brief overview of each architecture, a detailed introduction on how to use a program to explore this network, and a series of practical exercises that are designed to highlight the advantages, and disadvantages, of each and to provide a'road map' to the field of cognitive modeling. This book is designed to be used as a stand-alone volume, or a.

Print version record.