ElegansNet: a brief scientific report and initial experiments

TL;DR

ElegansNet is a neural network inspired by the C. elegans connectome that leverages biological topology to improve deep learning performance, outperforming traditional models on image classification and reconstruction tasks.

Contribution

This paper introduces ElegansNet, a novel neural network architecture based on the C. elegans connectome, demonstrating bio-inspired design benefits in deep learning.

Findings

ElegansNet outperforms randomly wired networks and models based on small-world properties.

ElegansNet achieves top-1 accuracy of 99.99% on Cifar10.

ElegansNet surpasses traditional deep learning models on image classification and reconstruction.

Abstract

This research report introduces ElegansNet, a neural network that mimics real-world neuronal network circuitry, with the goal of better understanding the interplay between connectome topology and deep learning systems. The proposed approach utilizes the powerful representational capabilities of living beings' neuronal circuitry to design and generate improved deep learning systems with a topology similar to natural networks. The Caenorhabditis elegans connectome is used as a reference due to its completeness, reasonable size, and functional neuron classes annotations. It is demonstrated that the connectome of simple organisms exhibits specific functional relationships between neurons, and once transformed into learnable tensor networks and integrated into modern architectures, it offers bio-plausible structures that efficiently solve complex tasks. The performance of the models is demonstrated against randomly wired networks and compared to artificial networks ranked on global benchmarks. In the first case, ElegansNet outperforms randomly wired networks. Interestingly, ElegansNet models show slightly similar performance with only those based on the Watts-Strogatz small-world property. When compared to state-of-the-art artificial neural networks, such as transformers or attention-based autoencoders, ElegansNet outperforms well-known deep learning and traditional models in both supervised image classification tasks and unsupervised hand-written digits reconstruction, achieving top-1 accuracy of 99.99% on Cifar10 and 99.84% on MNIST Unsup on the validation sets.