Using Connectome Features to Constrain Echo State Networks

TL;DR

This paper enhances Echo State Networks (ESNs) using connectome data, revealing how neurobiological structural features influence machine learning performance on chaotic time-series prediction tasks.

Contribution

It introduces connectome-derived modifications to ESNs and systematically studies their effects on prediction accuracy and variance, bridging neuroscience and machine learning.

Findings

Increasing clustering coefficient can improve performance.

Permuting weight positions may degrade accuracy.

Connectome features significantly influence ESN dynamics.

Abstract

We report an improvement to the conventional Echo State Network (ESN) across three benchmark chaotic time-series prediction tasks using fruit fly connectome data alone. We also investigate the impact of key connectome-derived structural features on prediction performance -- uniquely bridging neurobiological structure and machine learning function; and find that both increasing the global average clustering coefficient and modifying the position of weights -- by permuting their synapse-synapse partners -- can lead to increased model variance and (in some cases) degraded performance. In all we consider four topological point modifications to a connectome-derived ESN reservoir (null model): namely, we alter the network sparsity, re-draw nonzero weights from a uniform distribution, permute nonzero weight positions, and increase the network global average clustering coefficient. We compare the four resulting ESN model classes -- and the null model -- with a conventional ESN by conducting time-series prediction experiments on size-variants of the Mackey-Glass 17 (MG-17), Lorenz, and Rossler chaotic time series; denoting each model's performance and variance across train-validate trials.