A Distributed Backpropagation Algorithm of Neural Networks on Distributed-Memory Multiprocessors

In this paper, we present a distributed backpropagation algorithm of a fully connected multiarrayer neural network on a distributed-memory multiprocessor system. In our system, the neurons on each layer are partitioned into p disjoint sets and each set is mapped on a processor of a p-processor system. A fully distributed backpropagation algorithm, necessary communication pattern among the processors, and their time/space complexities are investigated. The p-processor speed-up of the backpropagation algorithm over a single processor is analyzed which can be used as a basis in determining the most cost-effective or optimal number of processors. The experimental results with a network of Transputers are also presented to confirm our model and analysis.
Publisher
IEEE
Issue Date
1990-10
Citation

Frontiers of Massively Parallel Computation, 1990. Proceedings., 3rd Symposium on the, pp.358-363

ISBN
0-8186-2053-6
URI
http://hdl.handle.net/10203/382
Appears in Collection
CS-Journal Papers(저널논문)
Files in This Item
컨퍼런스5.pdf(441.86 kB)Download
  • Hit : 595
  • Download : 444
  • Cited 0 times in thomson ci

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0