Modeling and Contractivity of Neural-Synaptic Networks with Hebbian Learning

TL;DR

This paper analyzes the stability and contractivity of neural-synaptic networks with Hebbian learning, providing conditions for robustness and biological plausibility in recurrent neural models.

Contribution

It introduces a low-dimensional formulation for neural networks with Hebbian learning and derives new stability and contractivity conditions based on biological parameters.

Findings

Networks satisfy Dale's Principle.

Provided a contractivity test based on biological quantities.

Numerical example demonstrates the theoretical results.

Abstract

This paper is concerned with the modeling and analysis of two of the most commonly used recurrent neural network models (i.e., Hopfield neural network and firing-rate neural network) with dynamic recurrent connections undergoing Hebbian learning rules. To capture the synaptic sparsity of neural circuits we propose a low dimensional formulation. We then characterize certain key dynamical properties. First, we give biologically-inspired forward invariance results. Then, we give sufficient conditions for the non-Euclidean contractivity of the models. Our contraction analysis leads to stability and robustness of time-varying trajectories -- for networks with both excitatory and inhibitory synapses governed by both Hebbian and anti-Hebbian rules. For each model, we propose a contractivity test based upon biologically meaningful quantities, e.g., neural and synaptic decay rate, maximum in-degree, and the maximum synaptic strength. Then, we show that the models satisfy Dale's Principle. Finally, we illustrate the effectiveness of our results via a numerical example.