Multilayer feedforward networks are universal approximators
Neural Networks
Independent component analysis, a new concept?
Signal Processing - Special issue on higher order statistics
Neural Computation
Hi-index | 0.00 |
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 wan t to revisite their model and giv e a rigorous mathematical framework in which this algorithm indeed converges to a demixing function.