Analysis and implementation of backpropagation neural networks on heterogeneous processor arrays
This study focuses on the parallel implementations of backpropagation (BP) neural net-works on a heterogeneous array of processors. A theoretical model of the BP algorithm running on the processor network was developed for training set parallelism and using this model the time for a training epoch w...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Published: |
2010
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/38978 |
| Summary: | This study focuses on the parallel implementations of backpropagation (BP) neural net-works on a heterogeneous array of processors. A theoretical model of the BP algorithm running on the processor network was developed for training set parallelism and using this model the time for a training epoch was predicted. The model made use of two graphical tools, process synchronization graphs and variable synchronization graphs, to aid in obtaining the theoretical expression for the time for a training epoch. The theoretically predicted epoch times from the model were then experimentally validated on well known benchmark problems. |
|---|