Analysis of an Adversarial Approach to Blind Source Separation
Juan Manuel Espinoza Bullón, Romis Ribeiro Attux, Levy Boccato
Evento: XXXVIII Simpósio Brasileiro de Telecomunicações e Processamento de Sinais (SBrT2020)
Keywords: Blind Source Separation Independent Component Analysis Adversarial Learning Autoencoders
AbstractIn this work, we analyze the adversarial network proposed by Brakel and Bengio at  to solve the problem of independent component analysis (ICA). Guided by a discriminator of independence, a linear autoencoder learns to codify a set of samples into estimates of their independent components. This is achieved by training the autoencoder to "fool the discriminator" and generate a code of latent variables. The present study focuses on linear mixtures, having the JADE and FastICA algorithms as benchmarks, but the paradigm has a significant potential of extension to more general scenarios.