Name
Abstract | ||
|---|---|---|
This paper presents a new efficient parallel implementation of neural networks on mesh-connected SIMD machines. A new algorithm to implement the recall and training phases of the multilayer perceptron network with back-error propagation is devised. The developed algorithm is much faster than other known algorithms of its class and comparable in speed to more complex architecture such as hypercube, without the added cost; it requires O(1) multiplications and O(log N) additions, whereas most others require O(N) multiplications and O(N) additions. The proposed algorithm maximizes parallelism by unfolding the ANN computation to its smallest computational primitives and processes these primitives in parallel. |
Year | DOI | Venue |
|---|---|---|
2003 | 10.1109/TPDS.2003.1233715 | IEEE Trans. Parallel Distrib. Syst. |
Keywords | Field | DocType |
added cost,developed algorithm,torus architecture,multilayer neural network,known algorithm,complex architecture,ann computation,proposed algorithm maximizes parallelism,mesh-connected simd machine,new efficient parallel implementation,new algorithm,back-error propagation,efficient mapping algorithm,multilayer perceptron,backpropagation,neural network,error propagation | Binary logarithm,Architecture,Computer science,Parallel computing,Torus,Multilayer perceptron,Artificial neural network,Backpropagation,Hypercube,Computation | Journal |
Volume | Issue | ISSN |
14 | 9 | 1045-9219 |
Citations | PageRank | References |
4 | 0.47 | 14 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Rafic A. Ayoubi | 1 | 66 | 7.60 |
| M. A. Bayoumi | 2 | 53 | 11.52 |