Title :
A theory of over-learning in the presence of noise
Author :
Yamasaki, Kazutaka ; Ogawa, Hidemitsu
Author_Institution :
Dept. of Comput. Sci., Tokyo Inst. of Technol., Japan
Abstract :
The over-learning problem for multilayer feedforward neural networks is discussed. A framework is proposed for the over-learning problem with noise free training data. It is shown that the framework is still valid in the case of noisy training data. It is applied to the case where the rote memorization criterion is used as a substitute for the Wiener criterion. Necessary and sufficient conditions for two kinds of admissibility of the rote memorization criterion by the Wiener criterion are obtained. These conditions lead to a method for choosing a training set which prevents Wiener-over-learning
Keywords :
feedforward neural nets; learning (artificial intelligence); Wiener criterion; admissibility; multilayer feedforward neural networks; noise free training data; over-learning problem; rote memorization criterion; Computer science; Feedforward neural networks; Intelligent networks; Inverse problems; Multi-layer neural network; Neural networks; Presses; Sufficient conditions; Training data; Vectors;
Conference_Titel :
Neural Networks, 1993., IEEE International Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-0999-5
DOI :
10.1109/ICNN.1993.298605
