Most practical applications of artificial neural networks are based on acomputational model involving the propagation of continuous variables from one processing unit tothe next. In recent years, data from neurobiological experiments have made it increasingly clearthat biological neural networks, which communicate through pulses, use the timing of the pulses totransmit information and perform computation. This realization has stimulated significant researchon pulsed neural networks, including theoretical analyses and model development, neurobiologicalmodeling, and hardware implementation. This book presents the complete spectrum ofcurrent research in pulsed neural networks and includes the most important work from many of the keyscientists in the field. Terrence J. Sejnowski's foreword, qNeural Pulse Coding, q presents anoverview of the topic. The first half of the book consists of longer tutorial articles spanningneurobiology, theory, algorithms, and hardware. The second half contains a larger number of shorterresearch chapters that present more advanced concepts. The contributors use consistent notation andterminology throughout the book. Contributors: Peter S. Burge, Stephen R. Deiss, Rodney J. Douglas, John G. Elias, Wulfram Gerstner, Alister Hamilton, David Horn, Axel Jahnke, Richard Kempter, Wolfgang Maass, Alessandro Mortara, Alan F. Murray, David P. M. Northmore, IritOpher, Kostas A. Papathanasiou, Michael Recce, Barry J. P. Rising, Ulrich Roth, Tim SchApnauer, Terrence J. Sejnowski, John Shawe-Taylor, Max R. van Daalen, J. Leo van Hemmen, Philippe Venier, Hermann Wagner, Adrian M. Whatley, Anthony M. Zador.One of the major advantages of analog systems is that the physical processes that contribute to a particular ... Unfortunately, technical limitations restrict the spatial extent over which fine-grained parallel analog processing circuits can be built. For example, the two and a half dimensional structure of present day silicon circuits, and the computational hardness of ... The continuous neuronal membrane of the dendrites and soma is divided into a series of homogeneous, isopotentialanbsp;...
|Title||:||Pulsed Neural Networks|
|Author||:||Wolfgang Maass, Christopher M. Bishop|
|Publisher||:||MIT Press - 2001-01|