Buch, Englisch, 428 Seiten, Print PDF, Format (B × H): 168 mm x 240 mm, Gewicht: 733 g
Buch, Englisch, 428 Seiten, Print PDF, Format (B × H): 168 mm x 240 mm, Gewicht: 733 g
ISBN: 978-0-19-852432-8
Verlag: Oxford University Press
The aim of this book is to describe the types of computation that can be performed by biologically plausible neural networks, and to show how these may be implemented in different systems in the brain. Neural Networks and Brain Function is structured in three sections, each of which addresses a different need in the market. The first section introduces and describes the operation of several fundamental types of neural network. The second section describes real neural networks in several brain systems, and shows how it is becoming possible to construct theories about how some parts of the brain work; it also provides an indication of the different neuroscience and neurocomputation techniques that will need to be combined to ensure further rapid progress in understanding how parts of the brain work. The third section, a collection of appendices, introduces the more formal quantitative approaches to many of the networks described. This is a clearly written and thoughtfully structured introduction to a fascinating and complex field of neuroscience. It will be a key text for researchers, graduate students and advanced undergraduates in the field, particularly for those without a background in computer science.
Autoren/Hrsg.
Fachgebiete
Weitere Infos & Material
- Ch. 1. Introduction
- Ch. 2. Pattern Association Memory
- Ch. 3. Autoassociation Memory
- Ch. 4. Competitive Networks, Including Self-Organizing Maps
- Ch. 5. Error-Correcting Networks: Perceptrons, Backpropagation of Error in Multilayer Networks, and Reinforcement Learning Algorithms
- Ch. 6. Hippocampus and Memory
- Ch. 7. Pattern Association in the Brain: Amygdala and Orbitofrontal Cortex
- Ch. 8. Cortical Networks for Invariant Pattern Recognition
- Ch. 9. Motor Systems: Cerebellum and Basal Ganglia
- Ch. 10. Cerebral Neocortex
- Appendix 1. Introduction to Linear Algebra for Neural Networks
- Appendix 2. Information Theory
- Appendix 3. Pattern Associators
- Appendix 4. Autoassociators
- Appendix 5. Recurrent Dynamics
