A Training Algorithm for Multilayer Neural Networks of Hard-Limiting Units with Random Bias (Special Section of Papers Selected from ITC-CSCC'99)

概要

論文の詳細を見る
The conventional back-propagation algorithm cannot be applied to networks of units having hard-limiting output functions, because these functions cannot be differentiated. In this paper, a gradient descent algorithm suitable for training multilayer feedforward networks of units having hard-limiting output functions, is presented. In order to get a differentiable output function for a hard-limiting unit, we utilized that if the bias of a unit in such a network is a random variable with smooth distribution function, the probability of the unit's output being in a particular state is a continuously differentiable function of the unit's inputs. Three simulatin results are given, which show that the performance of this algorithm is similar to that of the conventional back-propagation.
社団法人電子情報通信学会の論文
2000-06-25