single-jc.php

JACIII Vol.8 No.6 pp. 627-632
doi: 10.20965/jaciii.2004.p0627
(2004)

Paper:

Views over last 60 days: 470

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
Published:
November 20, 2004
Creative Commons License
Keywords:
multilayer neural network, back propagation, convergence, nonlinear identification
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.

Cite this article as:
Hiroshi Shiratsuchi, Hiromu Gotanda, Katsuhiro Inoue, and Kousuke Kumamaru, “Separability Conditions for Multilayer Nets Having Solutions and Convergent Superiority of Bipolar Nets,” J. Adv. Comput. Intell. Intell. Inform., Vol.8, No.6, pp. 627-632, 2004.
Data files:

Creative Commons License  This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on May. 16, 2022