Title | ||
---|---|---|
An efficient implementation of a backpropagation learning algorithm on a Quadrics parallel supercomputer |
Abstract | ||
---|---|---|
A parallel implementation of a library to build and train Multi LayerPerceptrons via the Back Propagation algorithm is presented. The targetmachine is the SIMD massively parallel supercomputer Quadrics. Performancemeasures are provided on three different machines with different number ofprocessors, for two network examples. A sample source code is given.IntroductionIn the beginning of their history, artificial neural networks architectures wereemployed to mimic in an extremely... |
Year | DOI | Venue |
---|---|---|
1995 | 10.1007/BFb0046697 | HPCN Europe |
Keywords | Field | DocType |
quadrics parallel supercomputer,efficient implementation,artificial neural network,backpropagation,source code | Back propagation algorithm,Supercomputer,Source code,Massively parallel,Computer science,Parallel computing,SIMD,Backpropagation,Rprop,Quadric | Conference |
Volume | ISSN | ISBN |
919 | 0302-9743 | 3-540-59393-4 |
Citations | PageRank | References |
3 | 0.56 | 5 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sergio Taraglio | 1 | 15 | 4.98 |
Federico Massaioli | 2 | 224 | 18.05 |