AN EFFICIENT MAPPING ALGORITHM OF MULTILAYER PERCEPTRON ON MESH-CONNECTED ARCHITECTURES
作者:
R. AYOUBI,
M. BAYOUMI,
A. ELCHOUEMI,
B. ALHALABI,
期刊:
Parallel Algorithms and Applications
(Taylor Available online 1997)
卷期:
Volume 11,
issue 3-4
页码: 273-285
ISSN:1063-7192
年代: 1997
DOI:10.1080/10637199708915598
出版商: Taylor & Francis Group
关键词: Algorithmic mapping;neural networks;mesh architecture;back propagation
数据来源: Taylor
摘要:
This paper represents 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 feedforward network with backpropagation is devised. The developed algorithm is considered much faster than other known algorithms; it requires O(l) multiplications and O(logN) additions, whereas most others require O(N) multiplications and O(N) additions. In this paper we restrict the algorithm to map a neural network of a maximum of n neurons per layer on anN × Nmesh of processors whereN ≥ n, however, it may be extended to the general case. Time comparisons with other algorithms are furnished.
点击下载:
PDF (217KB)
返 回