Characterization of canonical robust template values for a class of uncoupled CNNs implementing linearly separable Boolean functions

Authors:
Yih-Lon Lin;Wei-Chih Teng;Jyh-Horng Jeng;Jer-Guang Hsieh
Affiliations:
Dep. of Electrical Eng., National Sun Yat-Sen Uni., Kaohsiung, Taiwan;Dep. of Electrical Eng., National Sun Yat-Sen Uni., Kaohsiung, Taiwan;Dep. of Information Eng., I-Shou University, Kaohsiung County, Taiwan;Dep. of Electrical Eng., National Sun Yat-Sen Uni., Kaohsiung, Taiwan
Venue:
ICCOMP'05 Proceedings of the 9th WSEAS International Conference on Computers
Year:
2005

Citing 5
Cited 0

A training algorithm for optimal margin classifiers

COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
The nature of statistical learning theory

The nature of statistical learning theory
An introduction to support Vector Machines: and other kernel-based learning methods

An introduction to support Vector Machines: and other kernel-based learning methods
Cellular Neural Networks and Visual Computing

Cellular Neural Networks and Visual Computing
Morphology and autowave metric on CNN applied to bubble-debris classification

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, the geometric margin is used as a robustness indicator of a CNN (cellular neural network) implementing a linearly separable Boolean function. For a class of uncoupled CNNs having low template values, characterization of canonical robust template values is made by finding the maximal margin canonical hyperplane. Support vector machine (SVM) technique is employed for the associated optimization problem. Two illustrative examples are provided to illustrate the main result.