Training and Optimizing Distributed Neural Networks Using a Genetic Algorithm
Parallelizing neural networks is an active area of research. Current approaches surround the parallelization of the widely used back-propagation (BP) algorithm, which has a large amount of communication overhead, making it less than ideal for parallelization. An algorithm that does not depend on the...
| Main Author: | |
|---|---|
| Format: | Others |
| Published: |
NSUWorks
2010
|
| Subjects: | |
| Online Access: | http://nsuworks.nova.edu/gscis_etd/243 http://nsuworks.nova.edu/cgi/viewcontent.cgi?article=1242&context=gscis_etd |