Title :
Parallel implementation of backpropagation on transputers
Author :
Foo, S.K. ; Saratchandran, P. ; Sundararajan, N.
Author_Institution :
Sch. of Electr. & Electron. Eng., Nanyang Technol. Univ., Singapore
Abstract :
Backpropagation algorithm is one of the most popular training algorithms for multilayer feedforward neural networks. However training the network with this algorithm has proved to be computationally intensive for a sequential machine. In this paper, parallel implementation of the backpropagation algorithm is investigated using transputers hosted by a personal computer. Two methods of transputer implementations were considered. One method was the multi-tasking approach and the other the processor farming approach. Results showed that for all test cases, the training time for the neural network with the multi-tasking approach is shorter than the processor farming approach. Comparing with a serial 486-33 PC, it is found that as the problem size scales up, the improvement in training time from the parallel implementation becomes significant.
Keywords :
backpropagation; feedforward neural nets; parallel processing; sequential machines; transputer systems; backpropagation; learning algorithms; multi-tasking approach; multilayer feedforward neural networks; parallel; processor farming approach; sequential machine; transputers; Backpropagation algorithms; Computer errors; Computer networks; Electronic mail; Feedforward neural networks; Hardware; Microcomputers; Multi-layer neural network; Neural networks; Testing;
Conference_Titel :
Neural Networks, 1993. IJCNN '93-Nagoya. Proceedings of 1993 International Joint Conference on
Print_ISBN :
0-7803-1421-2
DOI :
10.1109/IJCNN.1993.714365
