Parallel Architectures for Artificial Neural Networks: Paradigms and Implementations

An excellent reference for neural networks research and application, this book covers the parallel implementation aspects of all major artificial neural network models in a single text. Parallel Architectures for Artificial Neural Networks details implementations on various processor architectures built on different hardware platforms, ranging from large, general purpose parallel computers to custom built MIMD machine.
Working experts describe their implementation research including results that are then divided into three sections:The theoretical analysis of parallel implementation schemes on MIMD message passing machinesThe details of parallel implementation of BP neural networks on general purpose, large, parallel computersFour specific purpose parallel neural computer configuration
Aimed at graduate students and researchers working in artificial neural networks and parallel computing this work can be used by graduate level educators to illustrate parallel computing methods for ANN simulation. Practitioners will also find the text an ideal reference tool for lucid mathematical analyses.

Spis treści:
1. Introduction (N. Sundararajan, P. Saratchandran, Jim Torresen).
2. A Review of Parallel Implementations of Backpropagation Neural Networks (Jim Torresen, Olav Landsverk).
I: Analysis of Parallel Implementations.
3. Network Parallelism for Backpropagation Neural Networks on a Heterogeneous Architecture (R. Arularasan, P. Saratchandran, N. Sundararajan, Shou King Foo).
4. Training–Set Parallelism for Backpropagation Neural Networks on a Heterogeneous Architecture (Shou King Foo, P. Saratchandran, N. Sundararajan).
5. Parallel Real–Time Recurrent Algorithm for Training Large Fully Recurrent Neural Networks (Elias S. Manolakos, George Kechriotis).
6. Parallel Implementation of ART1 Neural Networks on Processor Ring Architectures (Elias S. Manolakos, Stylianos Markogiannakis).
II: Implementations on a Big General–Purpose Parallel Computer.
7. Implementation of Backpropagation Neural Networks on Large Parallel Computers (Jim Torresen, Shinji Tomita).
III: Special Parallel Architectures and Application Case Studies.
8. Massively Parallel Architectures for Large–Scale Neural Network Computations (Yoshiji Fujimoto).
9. Regularly Structured Neural Networks on the DREAM Machine (Soheil Shams, Jean–Luc Gaudiot).
10. High–Performance Parallel Backpropagation Simulation with On–Line Learning (Urs A. Muller, Patrick Spiess, Michael Kocheisen, Beat Flepp, Anton Gunzinger, Walter Guggenbuhl).
11. Training Neural Networks with SPERT–II (Krste Asanovic;, James Beck, David Johnson, Brian Kingsbury, Nelson Morgan, John Wawrzynek).
12. Concluding Remarks (N. Sundararajan, P. Saratchandran).

Okładka tylna:
An excellent reference for neural networks research and application, this book covers the parallel implementation aspects of all major artificial neural network models in a single text. Parallel Architectures for Artificial Neural Networks details implementations on various processor architectures built on different hardware platforms, ranging from large, general purpose parallel computers to custom built MIMD machine.
Working experts describe their implementation research including results that are then divided into three sections:The theoretical analysis of parallel implementation schemes on MIMD message passing machinesThe details of parallel implementation of BP neural networks on general purpose, large, parallel computersFour specific purpose parallel neural computer configuration
Aimed at graduate students and researchers working in artificial neural networks and parallel computing this work can be used by graduate level educators to illustrate parallel computing methods for ANN simulation. Practitioners will also find the text an ideal ref erence tool for lucid mathematical analyses.