Title :
The analysis of the faulty behavior of synchronous neural networks
Author :
Belfore, Lee A., II ; Johnson, Barry W.
Author_Institution :
Dept. of Electr. & Comput. Eng., Marquette Univ., Milwaukee, WI, USA
fDate :
12/1/1991 12:00:00 AM
Abstract :
A means for analyzing the faulty behavior of neural networks is presented. Using an analogy between statistical physics and neural networks, a method for assessing the performance of a synchronous neural network model in the presence of faults is developed. Analytical predictions are computed using the statistical physics analogy and compared with the simulated behavior for two neuron models. An example of the analytical technique applied to an autoassociative memory is described
Keywords :
content-addressable storage; fault tolerant computing; neural nets; analytical predictions; faulty behavior; performance assessment; simulated behavior; statistical physics; synchronous neural networks; Biological system modeling; Computer networks; Computer vision; Fault tolerance; Image segmentation; Labeling; Layout; Neural networks; Physics; Speech processing;
Journal_Title :
Computers, IEEE Transactions on
