Fundamentals of Artificial Neural Networks - Tapa dura

This text provides a systematic account of artificial neural network paradigms by identifying the fundamental concepts and major methodologies underlying most of the current theory and practice employed by neural network researchers. The aim of such a systematic and unified treatment is to make the subject more accessible to students and practitioners. Important results are integrated in order to explain a wide range of existing empirical observations and commonly used heuristics. There are numerous illustrative examples, over 200 end-of-chapter analytical and computer-based problems that will aid in the development of neural network analysis and design skills, and a bibliography of nearly 700 references. The first two chapters present the basic concepts of artificial neural networks and analyze the computational capabilities of the basic network architectures involved. Supervised, reinforcement and unsupervised learning rules in simple nets are brought together in a common framework in Chapter Three. The convergence and solution properties of these learning rules are then examined in Chapter Four, using the "average learning equation" analysis approach. Learning multilayer nets are described in Chapter Five whilst Chapter Six covers neural network paradigms and associative memories and energy minimizing nets are considered in the next chapter. The final chapter takes up Boltzmann machines and Boltzmann learning along with other global search/optimization algorithms.