For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
A Training Algorithm for Multilayer Neural Networks of Hard-Limiting Units with Random Bias
Hongbing ZHU Kei EGUCHI Toru TABATA
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2000/06/25
Print ISSN: 0916-8508
Type of Manuscript: Special Section PAPER (Special Section of Papers Selected from 1999 International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC'99))
hard-limiting, multilayer neural network, back-propagation algorithm, learning of neural networks, sigmoid and threshold functions,
Full Text: PDF>>
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 simulation results are given, which show that the performance of this algorithm is similar to that of the conventional back-propagation.