Differential ICA

Abstract

As an alternative to the conventional Hebb-type unsupervised learning, differential learning was studied in the domain of Hebb's rule [1] and decorrelation [2]. In this paper we present an ICA algorithm which employs differential learning, thus named as differential ICA. We derive a differential ICA algorithm in the framework of maximum likelihood estimation and random walk model. Algorithm derivation using the natural gradient and local stability analysis are provided. Usefulness of the algorithm is emphasized in the case of blind separation of temporally correlated sources and is demonstrated through a simple numerical example.