Pulsed Neural Networks: (Pulsed Neural Networks)

Most practical applications of artificial neural networks are based on a computational model involving the propagation of continuous variables from one processing unit to the next. In recent years, data from neurobiological experiments have made it increasingly clear that biological neural networks, which communicate through pulses, use the timing of the pulses to transmit information and perform computation. This realization has stimulated significant research on pulsed neural networks, including theoretical analyses and model development, neurobiological modeling, and hardware implementation.This book presents the complete spectrum of current research in pulsed neural networks and includes the most important work from many of the key scientists in the field. Terrence J. Sejnowski's foreword, "Neural Pulse Coding," presents an overview of the topic. The first half of the book consists of longer tutorial articles spanning neurobiology, theory, algorithms, and hardware. The second half contains a larger number of shorter research chapters that present more advanced concepts. The contributors use consistent notation and terminology 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, Irit Opher, Kostas A. Papathanasiou, Michael Recce, Barry J. P. Rising, Ulrich Roth, Tim Sch nauer, Terrence J. Sejnowski, John Shawe-Taylor, Max R. van Daalen, J. Leo van Hemmen, Philippe Venier, Hermann Wagner, Adrian M. Whatley, Anthony M. Zador

Table of Contents:
Basic concepts and models. Part 1 Spiking neurons: the problem of neural coding; neuron models; conclusions. Part 2 Computing with Spiking neurons: introduction; a formal computational model for a network of Spiking neurons; McCullogh-Pitts neurons versus Spiking neurons; computing with temporal patterns; computing with a space-rate code; computing with firing rates; firing rates and temporal correlations; networks of Spiking neurons for storing and retrieving information; computing on Spike trains; conclusions. Part 3 Pulse-based computation in VLSI neural networks: background; pulsed coding - a VLSI perspective; a MOSFET introduction; pulse generation VLSI; pulsed arithmetic in VLSI; learning in pulsed systems; summary and issues raised. Part 4 Encoding information in neuronal activity: introduction; synchronization and oscillations; temporal binding; phase coding; dynamic range and firing rate codes; interspike interval variability; synapses and rate coding; summary and implications. Part 5 Building silicon nervous systems with dendritic tree neuromorphs: introduction; implementation in VLSI; neuromorphs in action; conclusions. Part 6 A pulse-coded communications infrastructure: introduction; neuromorphic computational nodes; neuromorphic VLSI neurons; address event representation (AER); implementations of AER; silicon cortex; functional tests of silicon cortex; future research on AER neuromorphic systems. Part 7 Analog VLSI pulsed networks for perceptive processing: introduction; analog perceptive nets communication requirements; analysis of the NAPFM communication system; address coding; silicon retina equipped with the NAPFM communication system; projective field generation; description of the integrated circuit for orientation enhancement; display interface; conclusion. Part 8 Preprocessing for pulsed neural VLSI systems: introduction; a sound segmentation system; signal processing in analog VLSI; Palmo - pulse based signal processing; conclusions; further works. Part 9 Digital simulation of Spiking neural networks: introduction; implementation issues of pulse-coded neural networks; programming environment; concepts of efficient simulation; mapping neural networks on parallel computers; performance study. Part 10 Populations of Spiking neurons: introduction; model; population activity equation; noise-free population dynamics; locking; transients; incoherent firing; conclusions. Part 11 Collective excitation phenomena and their applications: introduction; synchronization of pulse coupled oscillators; clustering via temporal segmentation; limits on temporal segmentation; image analysis; solitary waves; the importance of noise; conclusions. Part 12 Computing and learning with dynamic synapses: introduction; biological data on dynamic synapses; quantitative models; on the computational role of dynamic synapses; implications for learning in pulsed neural nets; conclusions. (Part contents)

About the Author :
Wolfgang Maass is Professor at the Institute for Theoretical Computer Science, Technische Universit t Graz. Christopher M. Bishop is Assistant Director at Microsoft Research, Cambridge, and Professor of Computer Science at the University of Edinburgh.

Review :
"Pulsed Neural Networks is a welcome new breeze in the field of neuronal modeling. At last, the central issue of timing in neuronal network function is treated in its full depth - a must for anyone seriously interested in CNS function." - Rodolfo Llinas, Department of Physiology and Neuroscience, New York University Medical School"