Physics – Condensed Matter – Disordered Systems and Neural Networks
Scientific paper
2006-09-20
Neurocomputing 63, 125-137 (2004)
Physics
Condensed Matter
Disordered Systems and Neural Networks
14pages, 2 figures
Scientific paper
10.1016/j.neucom.2004.01.191
An important goal in neural map learning, which can conveniently be accomplished by magnification control, is to achieve information optimal coding in the sense of information theory. In the present contribution we consider the winner relaxing approach for the neural gas network. Originally, winner relaxing learning is a slight modification of the self-organizing map learning rule that allows for adjustment of the magnification behavior by an a priori chosen control parameter. We transfer this approach to the neural gas algorithm. The magnification exponent can be calculated analytically for arbitrary dimension from a continuum theory, and the entropy of the resulting map is studied numerically conf irming the theoretical prediction. The influence of a diagonal term, which can be added without impacting the magnification, is studied numerically. This approach to maps of maximal mutual information is interesting for applications as the winner relaxing term only adds computational cost of same order and is easy to implement. In particular, it is not necessary to estimate the generally unknown data probability density as in other magnification control approaches.
Claussen Jens Christian
Villmann Thomas
No associations
LandOfFree
Magnification Control in Winner Relaxing Neural Gas does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Magnification Control in Winner Relaxing Neural Gas, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Magnification Control in Winner Relaxing Neural Gas will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-350637