Paper:
Views over last 60 days: 533
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, 2003Accepted:September 6, 2004Published: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:
