Training MLPs layer-by-layer with the information potential

Authors:
Dongxin Xu;J. C. Principe
Affiliations:
Comput. NeuroEng. Lab., Florida Univ., Gainesville, FL, USA;-
Venue:
ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 02
Year:
1999

Citing 0
Cited 2

LEGClust—A Clustering Algorithm Based on Layered Entropic Subgraphs

IEEE Transactions on Pattern Analysis and Machine Intelligence
Multilayer perceptrons as classifiers guided by mutual information and trained with genetic algorithms

IDEAL'12 Proceedings of the 13th international conference on Intelligent Data Engineering and Automated Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

In the area of information processing one fundamental issue is how to measure the relationship between two variables based only on their samples. In a previous paper, the idea of information potential which was formulated from the so called quadratic mutual information was introduced, and successfully applied to problems such as blind source separation and pose estimation of SAR (synthetic aperture radar) Images. This paper shows how information potential can be used to train a MLP (multilayer perceptron) layer-by-layer, which provides evidence that the hidden layer of a MLP serves as an "information filter" which tries to best represent the desired output in that layer in the statistical sense of mutual information.