Learning sparsity in reservoir computing through a novel bio-inspired algorithm

TL;DR

This paper introduces a bio-inspired machine learning algorithm that optimizes sparsity in reservoir computing by adjusting node firing thresholds, inspired by the fruit fly brain, leading to improved classification and memorization.

Contribution

A novel algorithm combining gradient descent and MCMC to optimize sparsity in reservoir computing inspired by biological neural mechanisms.

Findings

Outperforms standard gradient descent in classification tasks

Leads to better memorization and convergence time

Demonstrates the benefits of learned sparse representations

Abstract

The mushroom body is the key network for the representation of learned olfactory stimuli in Drosophila and insects. The sparse activity of Kenyon cells, the principal neurons in the mushroom body, plays a key role in the learned classification of different odours. In the specific case of the fruit fly, the sparseness of the network is enforced by an inhibitory feedback neuron called APL, and by an intrinsic high firing threshold of the Kenyon cells. In this work we took inspiration from the fruit fly brain to formulate a novel machine learning algorithm that is able to optimize the sparsity level of a reservoir by changing the firing thresholds of the nodes. The sparsity is only applied on the readout layer so as not to change the timescales of the reservoir and to allow the derivation of a one-layer update rule for the firing thresholds. The proposed algorithm is a combination of learning a neuron-specific sparsity threshold via gradient descent and a global sparsity threshold via a Markov chain Monte Carlo method. The proposed model outperforms the standard gradient descent, which is limited to the readout weights of the reservoir, on two example tasks. It demonstrates how the learnt sparse representation can lead to better classification performance, memorization ability and convergence time.