
Input Noise Immunity of Multilayer Perceptrons
Author(s) -
Lee Youngjik,
Oh SangHoon
Publication year - 1994
Publication title -
etri journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.295
H-Index - 46
eISSN - 2233-7326
pISSN - 1225-6463
DOI - 10.4218/etrij.94.0194.0013
Subject(s) - robustness (evolution) , perceptron , multilayer perceptron , noise immunity , computer science , artificial neural network , pattern recognition (psychology) , nonlinear system , orthogonality , noise (video) , artificial intelligence , algorithm , mathematics , transmission (telecommunications) , telecommunications , biochemistry , chemistry , physics , geometry , quantum mechanics , image (mathematics) , gene
In this paper, the robustness of the artificial neural networks to noise is demonstrated with a multilayer perceptron, and the reason of robustness is due to the statistical orthogonality among hidden nodes and its hierarchical information extraction capability. Also, the misclassification probability of a well‐trained multilayer perceptron is derived without any linear approximations when the inputs are contaminated with random noises. The misclassification probability for a noisy pattern is shown to be a function of the input pattern, noise variances, the weight matrices, and the nonlinear transformations. The result is verified with a handwritten digit recognition problem, which shows better result than that using linear approximations.