Paper:
Language: English:

Separability Conditions for Multilayer Nets Having Solutions and Convergent Superiority of Bipolar Nets

Hiroshi Shiratsuchi^, Hiromu Gotanda^, Katsuhiro Inoue^, and Kousuke Kumamaru^***

Faculty of Engineering, University of the Ryukyus, Nishihara, Okinawa 903-0213, Japan
Kinki University School of Humanity-Oriented Science and Engineering
Faculty of Computer Science and Systems Engineering, Kyushu
Institute of Technology

Received: April 30, 2003

Accepted: September 6, 2004

Keywords: multilayer neural network, back propagation, convergence, nonlinear identification

Journal ref: Journal of Advanced Computational Intelligence and Intelligent Informatics, Vol.8, No.6 pp. 627-632, 2004

Abstract

Separability conditions are formulated for multilayer nets to have
solutions by a set of normal vectors orthogonal to separation
hyperplanes. Comparing separability conditions to distributions of
normal vectors with weights and biases initialized ordinarily by random numbers with a zero mean, we found that bipolar nets are superior to unipolar nets in convergence of the back propagation learning initialized in such an ordinary manner.

[Notice]
* "Preview" is the first 2 pages of the article. You don't need the registration.
* To read the PDF file you will then need to download and install the Adobe Reader.
Adobe Reader is free and available for download here: