Phi Learning Private Ltd
|Number of Pages
As book review editor of the IEEE Transactions on Neural Networks, Mohamad Hassoun has had the opportunity to assess the multitude of books on artificial neural networks that have appeared in recent years. Now, in Fundamentals of Artificial Neural Networks, he provides the first systematic account of artificial neural network paradigms by identifying clearly the fundamental concepts and major methodologies underlying most of the current theory and practice employed by neural network researchers. This text emphasizes fundamental theoretical aspects of the computational capabilities and learning abilities of artificial neural networks.
Adopts systematic and unified treatment of the subject to make. it more accessible to students and practitioners.
Integrates. important results to fully explain a wide range of existing empirical observations and commonly used heuristics.
Assumes the reader possesses enough familiarity with the concept of a system and the notion of a "state", as well as with the basic elements of Boolean algebra and switching theory.
Views artificial neural networks as parallel compu-tational models, with varying degrees of complexity, comprised of densely interconnected adaptive processing units.
Discusses majority of the network models that are more closely related to traditional mathematical and/or statistical models rather than to neurobiology models.
Outlines theories and techniques of artificial neural networks that are fairly mathematical.
Provides numerous illustrative examples at the end of each chapter, along with over 200 analytical and computer based problems to aid in the development of neural network analysis and design skills.
Contains a such bibliography with newly 700 references.
Table of Contents
Computational Capabilities of Artificial Neural Networks
Mathematical Theory of Neural Learning
Adaptive Multilayer Neural Networks I
Adaptive Multilayer Neural Networks II
Associative Neural Memories
Clobal Search Methods for Neural Networks