Share Email Print

Proceedings Paper

Adaptive versions of the Ho-Kashyap learning algorithm
Author(s): Mohamad H. Hassoun
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Three adaptive version of the Ho-Kashyap perceptron training algorithm are derived based on gradient descent strategies. These adaptive Ho-Kashyap (AHK) training rules are comparable in their complexity to the LMS and perceptron training rules and are capable of adaptively forming linear discriminant surfaces which guarantee linear separability and of positioning such surfaces for maximal classification robustness. In particular, a derived version called AHK II is capable of adaptively identifying critical input vectors lying close to class boundaries in linearly separable problems. We extend this algorithm as AHK III, which adds the capability of fast convergence to linear discriminant surfaces that are 'good' approximations for nonlinearly separable problems.

Paper Details

Date Published: 11 November 1991
PDF: 7 pages
Proc. SPIE 1558, Wave Propagation and Scattering in Varied Media II, (11 November 1991); doi: 10.1117/12.49652
Show Author Affiliations
Mohamad H. Hassoun, Wayne State Univ. (United States)

Published in SPIE Proceedings Vol. 1558:
Wave Propagation and Scattering in Varied Media II
Vijay K. Varadan, Editor(s)

© SPIE. Terms of Use
Back to Top