A stochastic and competitive network for the separation of sources

This paper presents an adaptive procedure for the linear and non-linear separation of signalswithnon-uniform,symmetricalprobabilitydistributions,basedonbothsimulatedannealing andcompetitivelearningmethodsbymeansofaneuralnetwork,consideringthepropertiesofthe vectorial spaces of signals, and using a multiple linearization in the mixture space.

• Type: Conference
• Year: 2001
• Where: ESANN
• Authors: Carlos García Puntonet, Ali Mansour, Manuel Rodríguez Álvarez, Beatriz Prieto, Ignacio Rojas Ruiz
• Keywords: Adaptive Procedure, ESANN 2001, ESANN 2007, Non-linear Separation, Vectorial Spaces