ElegansNet: a brief scientific report and initial experiments

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.

arXiv comment4 pages, short report before full paper submission

References in corpus (19)

• Adam: A Method for Stochastic Optimization
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Statistical mechanics of complex networks
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• ADADELTA: An Adaptive Learning Rate Method
• Transformer in Transformer
• Structural Properties of the Caenorhabditis elegans Neuronal Network
• Deep learning incorporating biologically-inspired neural dynamics
• Clustering Stability: An Overview
• DenMune: Density peak based clustering using mutual nearest neighbors
• Information content of colored motifs in complex networks
• An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems
• An Algorithm for Routing Vectors in Sequences
• Brain experiments imply adaptation mechanisms which outperform common AI learning algorithms
• Inferencing Based on Unsupervised Learning of Disentangled Representations
• Astroformer: More Data Might not be all you need for Classification
• Minimalistic Unsupervised Learning with the Sparse Manifold Transform
• A machine learning approach to investigate regulatory control circuits in bacterial metabolic pathways
• Signal metrics analysis of oscillatory patterns in bacterial multi-omic networks