
Mevcut:*
Library | Materyal Türü | Barkod | Yer Numarası | Durum |
|---|---|---|---|---|
Searching... Pamukkale Merkez Kütüphanesi | Kitap | 0017482 | QP363.3.A534 1995 | Searching... Unknown |
Bound With These Titles
On Order
Özet
Özet
Based on notes that have been class-tested for more than a decade, this text is aimed at cognitive science and neuroscience students who need to understand brain function in terms of computational modelling and at engineers who want to go beyond formal algorithms to applications and computing strategies. It offers an approach networks from a broad neuroscience and cognitive science perspective, with an emphasis on the biology and psychology behind the assumptions of the models, as well as on what the models might be used for. It describes the mathematical and computational tools needed and provides an account of the author's own ideas.
Reviews (1)
Choice Review
This book, written by one of the most distinguished scientists in the field of neural networks, fully lives up to the expectations one has for a work by such an eminent authority. Anderson provides a thorough introduction to all aspects of neural networks, making this book an excellent book for introductory studies at the undergraduate or beginning graduate level. A noteworthy feature is the appealing style of Anderson's writing and the pleasant way in which he fully and clearly explains the required mathematics. Because of these characteristics, the book would be very useful for general readers as well. Another special feature is the way the author integrates the engineering, psychological, and neuroscientific aspects seamlessly. Thirdly, the balanced critiques of the limitations as well as strengths of neural networks adds considerably to the value of the book, and the account in the last three chapters of the author's research would interest all researchers. Overall, the book is rated a MUST for libraries of all academic institutions as well as general libraries. All levels. R. Bharath; Northern Michigan University
Table of Contents
| Introduction |
| Acknowledgements |
| Properties of Single Neurons |
| Synaptic Integration and Neuron Models |
| Essential Vector Operations |
| Lateral Inhibition and Sensory Processing |
| Simple Matrix Operations |
| The Linear Associator: Background and Foundations |
| The Kinear Associator: Simulations |
| Early Network Models: The Perceptron |
| Gradient Descent Algorithms |
| Representation of Information |
| Applications of Simple Associators: Concept Formation and Object Motion |
| Energy and Neural Networks: Hopfield Networks and Boltzmann Machines |
| Nearest Neighbor Models |
| Adaptive Maps |
| The BSB Model: A Simple Nonlinear Autoassociative Neural Network |
| Associative Computation |
| Teaching Arithmetic to a Neural Network |
| Afterword |
| Index |
