Ho, Charlotte Yuk-Fan, Ling, Bingo Wing-Kuen, Nasir, Muhammad Habib Ullah et al, Lam, Hak-Keung and Iu, Herbert H C
(2008)
Properties of an invariant set of weights of perceptrons.
In: International Joint Conference on Neural Networks 2008, 1 - 8 June 2008, Hong Kong.
Full content URL: http://dx.doi.org/10.1109/IJCNN.2008.4634015
Properties_of_an_Invariant_Set_of_Weights_of_Perceptrons.pdf | | ![[img]](http://eprints.lincoln.ac.uk/style/images/fileicons/application_pdf.png) [Download] |
|
![[img]](http://eprints.lincoln.ac.uk/style/images/fileicons/application_pdf.png)  Preview |
|
PDF
Properties_of_an_Invariant_Set_of_Weights_of_Perceptrons.pdf
- Whole Document
1MB |
Item Type: | Conference or Workshop contribution (Paper) |
---|
Item Status: | Live Archive |
---|
Abstract
In this paper, the dynamics of weights of perceptrons are investigated based on the perceptron training algorithm. In particular, the condition that the system map is not injective is derived. Based on the derived condition, an invariant set that results to a bijective invariant map is characterized. Also, it is shown that some weights outside the invariant set will be moved to the invariant set. Hence, the invariant set is attracting. Computer numerical simulation results on various perceptrons with exhibiting various behaviors, such as fixed point behaviors, limit cycle behaviors and chaotic behaviors, are illustrated.
Additional Information: | In this paper, the dynamics of weights of perceptrons are investigated based on the perceptron training algorithm. In particular, the condition that the system map is not injective is derived. Based on the derived condition, an invariant set that results to a bijective invariant map is characterized. Also, it is shown that some weights outside the invariant set will be moved to the invariant set. Hence, the invariant set is attracting. Computer numerical simulation results on various perceptrons with exhibiting various behaviors, such as fixed point behaviors, limit cycle behaviors and chaotic behaviors, are illustrated. |
---|
Keywords: | weights of perceptrons, various behaviours, Perceptron training algorithm |
---|
Subjects: | H Engineering > H310 Dynamics |
---|
Divisions: | College of Science > School of Engineering |
---|
ID Code: | 2725 |
---|
Deposited On: | 25 Jun 2010 09:02 |
---|
Repository Staff Only: item control page