Cantitate/Preț
Produs
Total produse
Vezi coșul
Neural Networks: An Introduction de Berndt Müller

Neural Networks: An Introduction: Physics of Neural Networks

Autor Berndt Müller, Joachim Reinhardt, Michael T. Strickland
en Limba Engleză Paperback – 2 oct 1995
Neural Networks presents concepts of neural-network models and techniques of parallel distributed processing in a three-step approach: - A brief overview of the neural structure of the brain and the history of neural-network modeling introduces to associative memory, preceptrons, feature-sensitive networks, learning strategies, and practical applications. - The second part covers subjects like 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. - The final part discusses nine programs with practical demonstrations of neural-network models. The software and source code in C are on a 3 1/2" MS-DOS diskette can be run with Microsoft, Borland, Turbo-C, or compatible compilers.
Citește tot Restrânge

Din seria Physics of Neural Networks

  • 18% Models of Neural Networks: Temporal Aspects of Coding and Information Processing in Biological Systems
    Preț: 95352 lei
  • 20% Models of Neural Networks IV: Early Vision and Attention
    Preț: 33900 lei
  • Models of Neural Networks I
    Preț: 39313 lei
  • 15% Models of Neural Networks III: Association, Generalization, and Representation
    Preț: 64824 lei

Preț: 33849 lei

Preț vechi: 42311 lei
-20% Nou

Puncte Express: 508
Preț estimativ în valută:
6478€ • 6722$ • 5414£

Carte tipărită la comandă

Livrare economică 17-31 martie

 Adaugă în coș

Wish list
Gift list
Am citit!
Adaugă în listă
Preluare comenzi: 021 569.72.76

Specificații

ISBN-13: 9783540602071
ISBN-10: 3540602070
Pagini: 348
Ilustrații: XV, 331 p. With online files/update.
Dimensiuni: 155 x 235 x 18 mm
Greutate: 0.59 kg
Ediția:2nd updated and corr. ed.
Editura: Springer Berlin, Heidelberg
Colecția Springer
Seria Physics of Neural Networks

Locul publicării:Berlin, Heidelberg, Germany

Public țintă

Professional/practitioner

Cuprins

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.

Recenzii

"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

Textul de pe ultima copertă

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.