Berndt Müller, Joachim Reinhardt, Michael T. Strickland

Neural Networks (eBook, PDF)

An Introduction

• Format: PDF

Produktbeschreibung

Neural Networks The concepts of neural-network models and techniques of parallel distributed processing are comprehensively presented in a three-step approach: - After a brief overview of the neural structure of the brain and the history of neural-network modeling, the reader is introduced to associative memory, preceptrons, feature-sensitive networks, learning strategies, and practical applications. - The second part covers more advanced subjects such as the statistical physics of spin glasses, the mean-field theory of the Hopfield model, and the "space of interactions" approach to the storage capacity of neural networks. - In the self-contained final part, seven programs that provide practical demonstrations of neural-network models and their learning strategies are discussed. The software is included on a 3 1/2-inch MS-DOS diskette. The source code can be modified using Borland's TURBO-C 2.0 compiler, the Microsoft C compiler (5.0), or compatible compilers.

---

Dieser Download kann aus rechtlichen Gründen nur mit Rechnungsadresse in A, B, BG, CY, CZ, D, DK, EW, E, FIN, F, GR, HR, H, IRL, I, LT, L, LR, M, NL, PL, P, R, S, SLO, SK ausgeliefert werden.

Produktdetails

• Verlag: Springer Berlin Heidelberg
• Seitenzahl: 331
• Erscheinungstermin: 6. Dezember 2012
• Englisch
• ISBN-13: 9783642577604
• Artikelnr.: 53393598

Inhaltsangabe

1. The Structure of the Central Nervous System.- 2. Neural Networks Introduced.- 3. Associative Memory.- 4. Stochastic Neurons.- 5. Cybernetic Networks.- 6. Multilayered Perceptrons.- 7. Applications.- 8. More Applications of Neural Networks.- 9. Network Architecture and Generalization.- 10. Associative Memory: Advanced Learning Strategies.- 11. Combinatorial Optimization.- 12. VLSI and Neural Networks.- 13. Symmetrical Networks with Hidden Neurons.- 14. Coupled Neural Networks.- 15. Unsupervised Learning.- 16. Evolutionary Algorithms for Learning.- 17. Statistical Physics and Spin Glasses.- 18. The Hopfield Network for p/N' 0.- 19. The Hopfield Network for Finite p/N.- 20. The Space of Interactions in Neural Networks.- 21. Numerical Demonstrations.- 22. ASSO: Associative Memory.- 23. ASSCOUNT: Associative Memory for Time Sequences.- 24. PERBOOL: Learning Boolean Functions with Back-Prop.- 25. PERFUNC: Learning Continuous Functions with Back-Prop.- 26. Solution of the Traveling-Salesman Problem.- 27. KOHOMAP: The Kohonen Self-organizing Map.- 28. btt: Back-Propagation Through Time.- 29. NEUROGEN: Using Genetic Algorithms to Train Networks.- References.

Rezensionen

"I have enjoyed using the previous edition of this well-known book both as a personal text and as a class manual. Although it claims to be only an introduction, it contains a wealth of material and addresses real problems in physics." Computing Reviews