single-jc.php

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

Paper:

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
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:
H. Shiratsuchi, H. Gotanda, K. Inoue, and K. 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:

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

Last updated on Dec. 01, 2022