Evolving to learn: discovering interpretable plasticity rules for spiking networks

TL;DR

This paper introduces an automated evolutionary method to discover interpretable synaptic plasticity rules for spiking neural networks, enhancing understanding of biological learning and improving artificial system adaptability.

Contribution

It presents a novel symbolic evolution approach to find biophysically plausible, interpretable plasticity rules tailored to specific tasks, bridging biological plausibility and machine learning.

Findings

Discovered new reward-based learning mechanisms.

Recovered gradient-descent-like learning rules.

Identified functionally equivalent STDP-like rules with homeostasis.

Abstract

Continuous adaptation allows survival in an ever-changing world. Adjustments in the synaptic coupling strength between neurons are essential for this capability, setting us apart from simpler, hard-wired organisms. How these changes can be mathematically described at the phenomenological level, as so called "plasticity rules", is essential both for understanding biological information processing and for developing cognitively performant artificial systems. We suggest an automated approach for discovering biophysically plausible plasticity rules based on the definition of task families, associated performance measures and biophysical constraints. By evolving compact symbolic expressions we ensure the discovered plasticity rules are amenable to intuitive understanding, fundamental for successful communication and human-guided generalization. We successfully apply our approach to typical learning scenarios and discover previously unknown mechanisms for learning efficiently from rewards, recover efficient gradient-descent methods for learning from target signals, and uncover various functionally equivalent STDP-like rules with tuned homeostatic mechanisms.