Neuroscience-inspired online unsupervised learning algorithms

TL;DR

This paper introduces biologically plausible neural networks for unsupervised learning, inspired by neuroscience, capable of tasks like dimensionality reduction, clustering, and manifold learning, using similarity-based objective functions optimized online.

Contribution

It presents a new class of biologically plausible neural networks that optimize similarity-based objectives for unsupervised learning tasks, bridging neuroscience and machine learning.

Findings

Successfully performs dimensionality reduction and clustering

Uses local learning rules compatible with biological plausibility

Applies to various unsupervised learning tasks

Abstract

Although the currently popular deep learning networks achieve unprecedented performance on some tasks, the human brain still has a monopoly on general intelligence. Motivated by this and biological implausibility of deep learning networks, we developed a family of biologically plausible artificial neural networks (NNs) for unsupervised learning. Our approach is based on optimizing principled objective functions containing a term that matches the pairwise similarity of outputs to the similarity of inputs, hence the name - similarity-based. Gradient-based online optimization of such similarity-based objective functions can be implemented by NNs with biologically plausible local learning rules. Similarity-based cost functions and associated NNs solve unsupervised learning tasks such as linear dimensionality reduction, sparse and/or nonnegative feature extraction, blind nonnegative source separation, clustering and manifold learning.