ElegansNet: a brief scientific report and initial experiments

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Bardozzo, Francesco, Terlizzi, Andrea, Liò, Pietro, Tagliaferri, Roberto
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917625512067072
author Bardozzo, Francesco
Terlizzi, Andrea
Liò, Pietro
Tagliaferri, Roberto
author_facet Bardozzo, Francesco
Terlizzi, Andrea
Liò, Pietro
Tagliaferri, Roberto
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2304_13538
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle ElegansNet: a brief scientific report and initial experiments
Bardozzo, Francesco
Terlizzi, Andrea
Liò, Pietro
Tagliaferri, Roberto
Neural and Evolutionary Computing
Artificial Intelligence
68T07 (Primary)
I.2.0
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.
title ElegansNet: a brief scientific report and initial experiments
topic Neural and Evolutionary Computing
Artificial Intelligence
68T07 (Primary)
I.2.0
url https://arxiv.org/abs/2304.13538