| R. Linsker. An aplication of the principle of maximum information preservation to linear systems. In Advances in Neural Information Processing Systems, volume 1, pages 186-194. Morgan Kauman, San Mateo, CA, 1989. |
....In this paper we propose measures based on mutual information for evaluating the dependence among the outputs and the output errors of learning machines. Some of the main applications of mutual information to machine learning problems concern modeling of self organized systems and feature maps [23, 3], feature transformation and selection [13, 1, 5, 34, 30] image processing [2, 31] independent component analysis [6] We extend the application of mutual information to the evaluation of the dependence among outputs and among output errors in learning machines. The main idea behind the ....
R. Linsker. An aplication of the principle of maximum information preservation to linear systems. In Advances in Neural Information Processing Systems, volume 1, pages 186-194. Morgan Kauman, San Mateo, CA, 1989.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC