Journal of the Korean Institute of Telematics and Electronics C (전자공학회논문지C)
- Volume 34C Issue 1
- /
- Pages.28-41
- /
- 1997
- /
- 1226-5853(pISSN)
Parallel Implementation of A Neural Network Ensemble on the Connection Machine CM-2
Connection Machine CM-2상에서 신경망군(群)의 병렬 구현
Abstract
This paper describes a parallel implementation of a neurla network ensemble developed for object recognition on the connection machine CM-2. The implementation ensures that multiple networks are implemented simultaneously starting from different initial weights and all training samples are applied to each network by one sample per a copy of each network. When compared with a sequential implementation, this accelerates the computation speed by O(N.m.n) where N, m, and n are the network, respectively. The speedup in the computation time and the convergence characteristics of sthe modified backpropagation learning precedure were evaluated by two-dimensional object recognition problem.
Keywords