Title :
Robustness analysis of a class of neural networks
Author :
Liu, Derong ; Michel, Anthony N.
Author_Institution :
Dept. of Electr. Eng., Notre Dame Univ., IN, USA
Abstract :
We present a robustness analysis result for a class of neural networks. Specifically, we assume a set of bipolar vectors to be memories for a network, and we establish a sufficient condition under which the given set of vectors are also memories of the original network after perturbations on its parameters
Keywords :
content-addressable storage; network parameters; perturbation techniques; recurrent neural nets; associative memories; bipolar vectors; feedback neural networks; network parameters; perturbations; robustness analysis; Artificial intelligence; Associative memory; Equations; Intelligent networks; Network synthesis; Neural networks; Neurofeedback; Robust stability; Robustness; Sufficient conditions;
Conference_Titel :
Circuits and Systems, 1993., Proceedings of the 36th Midwest Symposium on
Conference_Location :
Detroit, MI
Print_ISBN :
0-7803-1760-2
DOI :
10.1109/MWSCAS.1993.343271
