Normative framework for deriving neural networks with multi-compartmental neurons and non-Hebbian plasticity

TL;DR

This paper develops a normative framework based on similarity matching that derives neural network models with multi-compartmental neurons and non-Hebbian plasticity, expanding understanding of complex brain structures and learning rules.

Contribution

It generalizes similarity matching to complex objectives, resulting in neural network models with multi-compartmental neurons and local, non-Hebbian learning rules.

Findings

Derives online algorithms mapping onto multi-compartmental neuron models

Addresses a broad class of unsupervised and self-supervised learning tasks

Provides a normative framework for non-Hebbian plasticity in the brain

Abstract

An established normative approach for understanding the algorithmic basis of neural computation is to derive online algorithms from principled computational objectives and evaluate their compatibility with anatomical and physiological observations. Similarity matching objectives have served as successful starting points for deriving online algorithms that map onto neural networks (NNs) with point neurons and Hebbian/anti-Hebbian plasticity. These NN models account for many anatomical and physiological observations; however, the objectives have limited computational power and the derived NNs do not explain multi-compartmental neuronal structures and non-Hebbian forms of plasticity that are prevalent throughout the brain. In this article, we unify and generalize recent extensions of the similarity matching approach to address more complex objectives, including a large class of unsupervised and self-supervised learning tasks that can be formulated as symmetric generalized eigenvalue problems or nonnegative matrix factorization problems. Interestingly, the online algorithms derived from these objectives naturally map onto NNs with multi-compartmental neurons and local, non-Hebbian learning rules. Therefore, this unified extension of the similarity matching approach provides a normative framework that facilitates understanding multi-compartmental neuronal structures and non-Hebbian plasticity found throughout the brain.