Biologically plausible single-layer networks for nonnegative independent component analysis

TL;DR

This paper develops biologically plausible single-layer neural network algorithms for nonnegative independent component analysis, enabling online blind source separation with local learning rules and nonnegative outputs.

Contribution

It introduces two novel single-layer network algorithms for NICA that improve upon previous multi-layer models, aligning with biological constraints.

Findings

Two algorithms for NICA with single-layer implementations

Algorithms operate online with local synaptic learning rules

Networks produce effective blind source separation results

Abstract

An important problem in neuroscience is to understand how brains extract relevant signals from mixtures of unknown sources, i.e., perform blind source separation. To model how the brain performs this task, we seek a biologically plausible single-layer neural network implementation of a blind source separation algorithm. For biological plausibility, we require the network to satisfy the following three basic properties of neuronal circuits: (i) the network operates in the online setting; (ii) synaptic learning rules are local; (iii) neuronal outputs are nonnegative. Closest is the work by Pehlevan et al. [Neural Computation, 29, 2925--2954 (2017)], which considers Nonnegative Independent Component Analysis (NICA), a special case of blind source separation that assumes the mixture is a linear combination of uncorrelated, nonnegative sources. They derive an algorithm with a biologically plausible 2-layer network implementation. In this work, we improve upon their result by deriving 2 algorithms for NICA, each with a biologically plausible single-layer network implementation. The first algorithm maps onto a network with indirect lateral connections mediated by interneurons. The second algorithm maps onto a network with direct lateral connections and multi-compartmental output neurons.