Pattern Repulsion Revisited

Marques and Almeida [9] recently proposed a nonlinear data seperation technique based on the maximum entropy principle of Bell and Sejnowsky. The idea behind is a pattern repulsion model alluding to repulsion of physical particles in a restricted system which leads to a uniform distribution, hence a maximum entropy, under certain conditions to the energy function. In this paper, we want to revisite their model and give a rigorous mathematical framework in which this algorithm indeed converges to a demixing function.

• Type: Conference
• Year: 2001
• Where: IWANN
• Authors: Fabian J. Theis, Christoph Bauer, Carlos García Puntonet, Elmar Wolfgang Lang
• Keywords: IWANN 2001, Maximum Entropy, Maximum Entropy Principle, Neural Networks, Pattern Repulsion Model