Title :
Reconfigurable fault tolerant neural network
Author :
Chen, Chung-Hsing ; Chu, Lon-Chan ; Saab, Daniel G.
Author_Institution :
Coordinated Sci. Lab., Illinois Univ., Urbana, IL, USA
Abstract :
A reconfigurable fault-tolerant multilayer feedforward neural network is presented. It addresses both fault detection and reconfiguration of a neural network in a unified manner. As a result, a neural network with low area overhead and high reliability is achieved. A concurrent error detection scheme on neural networks which consumes low hardware overhead and negligible time overhead is described. It is capable of detecting a single fault in each neuron of the network. The reconfiguration of this neural network is addressed. It features low complexity of interconnection and low hardware overhead
Keywords :
error correction; fault tolerant computing; feedforward neural nets; reconfigurable architectures; concurrent error detection; fault detection; low area overhead; reconfigurable fault-tolerant multilayer feedforward neural network; reliability; Circuit faults; Electrical fault detection; Fault detection; Fault tolerance; Feedforward neural networks; Multi-layer neural network; Neural network hardware; Neural networks; Neurons; Redundancy;
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
DOI :
10.1109/IJCNN.1992.226931