Title :
Inherent fault tolerance analysis for a class of multi-layer neural networks with weight deviations
Author :
Yang, Xiaofan ; Chen, Tinghuai
Author_Institution :
Comput. Inst., Chongqing Univ., Sichuan, China
Abstract :
The general formula of computing the deviation of the output of a multilayer neural network (MLNN) with respect to the deviations of its input and of its weights is presented. The upper bound of the deviation propagation from level to level is well estimated with certain probability. Based on this, one can analyze the relation between the topological structure of an MLNN and its fault tolerance property, which can be used to correctly design fault tolerant MLNNs
Keywords :
fault tolerant computing; feedforward neural nets; probability; topology; inherent fault tolerance analysis; multilayer neural network; probability; topological structure; upper bound; weight deviations; Character recognition; Computer networks; Concurrent computing; Distributed computing; Fault tolerance; Multi-layer neural network; Neural networks; Neurons; Target recognition; Upper bound;
Conference_Titel :
Neural Networks, 1993., IEEE International Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-0999-5
DOI :
10.1109/ICNN.1993.298700
