Research in neural modeling and neural networks has escalated dramatically in the last decade, acquiring along the way terms and concepts, such as learning, memory, perception, recognition, which are the basis of neuropsychology. Nevertheless, for many, neural modeling remains controversial in its purported ability to describe brain activity. The difficulties in "modeling" are various, but arise principally in identifying those elements that are fundamental for the expression (and description) of superior neural activity. This is complicated by our incomplete knowledge of neural structures and functions, at the cellular and population levels. The first step towards enhanced appreciation of the value of neural modeling and neural networks is to be aware of what has been achieved in this multidisciplinary field of research. This book sets out to create such awareness. Leading experts develop in twelve chapters the key topics of neural structures and functions, dynamics of single neurons, oscillations in groups of neurons, randomness and chaos in neural activity, (statistical) dynamics of neural networks, learning, memory and pattern recognition.

Neural Networks: Computational Models and Applications presents important theoretical and practical issues in neural networks, including the learning algorithms of feed-forward neural networks, various dynamical properties of recurrent neural networks, winner-take-all networks and their applications in broad manifolds of computational intelligence: pattern recognition, uniform approximation, constrained optimization, NP-hard problems, and image segmentation. The book offers a compact, insightful understanding of the broad and rapidly growing neural networks domain.

This book is a beginning graduate-level introduction to neural networks which is divided into four parts.

"This book introduces Higher Order Neural Networks (HONNs) to computer scientists and computer engineers as an open box neural networks tool when compared to traditional artificial neural networks"--Provided by publisher.

Provides an introduction to the neural network modeling of complex cognitive and neuropsychological processes. Over the past few years, computer modeling has become more prevalent in the clinical sciences as an alternative to traditional symbol-processing models. This book provides an introduction to the neural network modeling of complex cognitive and neuropsychological processes. It is intended to make the neural network approach accessible to practicing neuropsychologists, psychologists, neurologists, and psychiatrists. It will also be a useful resource for computer scientists, mathematicians, and interdisciplinary cognitive neuroscientists. The editors (in their introduction) and contributors explain the basic concepts behind modeling and avoid the use of high-level mathematics. The book is divided into four parts. Part I provides an extensive but basic overview of neural network modeling, including its history, present, and future trends. It also includes chapters on attention, memory, and primate studies. Part II discusses neural network models of behavioral states such as alcohol dependence, learned helplessness, depression, and waking and sleeping. Part III presents neural network models of neuropsychological tests such as the Wisconsin Card Sorting Task, the Tower of Hanoi, and the Stroop Test. Finally, part IV describes the application of neural network models to dementia: models of acetycholine and memory, verbal fluency, Parkinsons disease, and Alzheimer's disease. Contributors J. Wesson Ashford, Rajendra D. Badgaiyan, Jean P. Banquet, Yves Burnod, Nelson Butters, John Cardoso, Agnes S. Chan, Jean-Pierre Changeux, Kerry L. Coburn, Jonathan D. Cohen, Laurent Cohen, Jose L. Contreras-Vidal, Antonio R. Damasio, Hanna Damasio, Stanislas Dehaene, Martha J. Farah, Joaquin M. Fuster, Philippe Gaussier, Angelika Gissler, Dylan G. Harwood, Michael E. Hasselmo, J, Allan Hobson, Sam Leven, Daniel S. Levine, Debra L. Long, Roderick K. Mahurin, Raymond L. Ownby, Randolph W. Parks, Michael I. Posner, David P. Salmon, David Servan-Schreiber, Chantal E. Stern, Jeffrey P. Sutton, Lynette J. Tippett, Daniel Tranel, Bradley Wyble

The purpose of this book is to introduce and survey the various quantitative methods which have been proposed for describing, simulating, embodying, or characterizing the processing of electrical signals in nervous systems. We believe that electrical signal processing is a vital determinant of the functional organization of the brain, and that in unraveling the inherent complexities of this processing it will be essential to utilize the methods of quantification and modeling which have led to crowning successes in the physical and engineering sciences. In comprehensive terms, we conceive neural modeling to be the attempt to relate, in nervous systems, function to structure on the basis of operation. Sufficient knowledge and appropriate tools are at hand to maintain a serious and thorough study in the area. However, work in the area has yet to be satisfactorily integrated within contemporary brain research. Moreover, there exists a good deal of inefficiency within the area resulting from an overall lack of direction, critical self-evaluation, and cohesion. Such theoretical and modeling studies as have appeared exist largely as fragmented islands in the literature or as sparsely attended sessions at neuroscience conferences. In writing this book, we were guided by three main immediate objectives. Our first objective is to introduce the area to the upcoming generation of students of both the hard sciences and psychological and biological sciences in the hope that they might eventually help bring about the contributions it promises.