ICA

Nonlinear ICA using Time-contrastive learning

July 31, 2024
Statistics
ICA, NonlinearICA

We learn features that enable discriminating data points from different time segments We use ordinary neural network training: Last hidden layer gives the features Surprising theoretical result: Estimates a nonlinear ICA model with general nonlinear mixing $x(t) = f(s(t))$ nonstationary components $s_{i}(t)$