Ho, Charlotte Yuk-Fan and Ling, Bingo Wing-Kuen and IU, Herbert Ho-Ching (2010) Invariant set of weight of perceptron trained by perceptron training algorithm. IEEE Transaction on Systems, Man, and Cybernetics, 40 (6). pp. 1521-1530. ISSN 0018-9472

Preview

PDF Invariant_Set_of_Weight_of_Perceptron.pdf - Whole Document Download (1317Kb)

Abstract

In this paper, an invariant set of the weight of the perceptron trained by the perceptron training algorithm is defined and characterized. The dynamic range of the steady state values of the weight of the perceptron can be evaluated via finding the dynamic range of the weight of the perceptron inside the largest invariant set. Also, the necessary and sufficient condition for the forward dynamics of the weight of the perceptron to be injective as well as the condition for the invariant set of the weight of the perceptron to be attractive is derived.

Item Type:	Article
Additional Information:	In this paper, an invariant set of the weight of the perceptron trained by the perceptron training algorithm is defined and characterized. The dynamic range of the steady state values of the weight of the perceptron can be evaluated via finding the dynamic range of the weight of the perceptron inside the largest invariant set. Also, the necessary and sufficient condition for the forward dynamics of the weight of the perceptron to be injective as well as the condition for the invariant set of the weight of the perceptron to be attractive is derived.
Keywords:	Perceptron training algorithm, neurodynamics, symbolic dynamics, chaos, invariant set
Subjects:	H Engineering > H310 Dynamics
Divisions:	College of Sciences > Faculty of Science > Lincoln School of Engineering
Depositing User:	Rosaline Smith
Date Deposited:	11 Jun 2010 19:55
Last Modified:	13 Mar 2013 08:39
URI:	http://eprints.lincoln.ac.uk/id/eprint/2684

Actions (login required)

View Item