Blind Source Separation with Neural Networks

Student: Diana Kroytor

Project Goal

• Development of a two-layer neural network ICA architecture maximizing the entropy of the outputs with logistic transfer function.

• Design of a neural architecture for nonlinear three-layer ICA network for estimating the respective basis vectors. They are counterparts of the PCA eigenvectors, but characterize the data in many cases better. The purpose of the three layers is: a) whitening of the input data for yielding good separation results; b) separation of independent sources (components); c) estimation of the basis vectors.

• Application of the above neural networks on benchmark sets.