Correlative Information Maximization Based Biologically Plausible Neural Networks for Correlated Source Separation

TL;DR

This paper introduces a biologically plausible neural network that can extract correlated latent sources by maximizing correlative information transfer, overcoming the independence assumption of previous models.

Contribution

It proposes a novel neural network framework that relaxes the independence constraint, enabling extraction of correlated sources using local learning rules.

Findings

Demonstrates superior separation of correlated sources in synthetic data.

Shows effectiveness on natural source data.

Provides a flexible model for complex latent structures.

Abstract

The brain effortlessly extracts latent causes of stimuli, but how it does this at the network level remains unknown. Most prior attempts at this problem proposed neural networks that implement independent component analysis which works under the limitation that latent causes are mutually independent. Here, we relax this limitation and propose a biologically plausible neural network that extracts correlated latent sources by exploiting information about their domains. To derive this network, we choose maximum correlative information transfer from inputs to outputs as the separation objective under the constraint that the outputs are restricted to their presumed sets. The online formulation of this optimization problem naturally leads to neural networks with local learning rules. Our framework incorporates infinitely many source domain choices and flexibly models complex latent structures. Choices of simplex or polytopic source domains result in networks with piecewise-linear activation functions. We provide numerical examples to demonstrate the superior correlated source separation capability for both synthetic and natural sources.