Imposing Connectome-Derived Topology on an Echo State Network

TL;DR

This study explores how incorporating a fruit fly connectome's topology into an Echo State Network improves chaotic time series prediction, demonstrating that biologically inspired connectivity can enhance reservoir computing performance.

Contribution

The paper introduces a novel approach of using connectome-derived topology in ESNs, showing improved performance over traditional random reservoirs in chaotic time series tasks.

Findings

FFESNs outperform or have lower variance than standard ESNs.

Connectome-based reservoirs can enhance reservoir computing models.

Biologically inspired topologies improve chaotic time series prediction.

Abstract

Can connectome-derived constraints inform computation? In this paper we investigate the contribution of a fruit fly connectome's topology on the performance of an Echo State Network (ESN) -- a subset of Reservoir Computing which is state of the art in chaotic time series prediction. Specifically, we replace the reservoir layer of a classical ESN -- normally a fixed, random graph represented as a 2-d matrix -- with a particular (female) fruit fly connectome-derived connectivity matrix. We refer to this experimental class of models (with connectome-derived reservoirs) as "Fruit Fly ESNs" (FFESNs). We train and validate the FFESN on a chaotic time series prediction task; here we consider four sets of trials with different training input sizes (small, large) and train-validate splits (two variants). We compare the validation performance (Mean-Squared Error) of all of the best FFESN models to a class of control model ESNs (simply referred to as "ESNs"). Overall, for all four sets of trials we find that the FFESN either significantly outperforms (and has lower variance than) the ESN; or simply has lower variance than the ESN.