This paper introduces Elegans-AI models, a class of neural networks that leverage the connectome topology of the Caenorhabditis elegans to design deep and reservoir architectures. Utilizing deep learning models inspired by the connectome, this paper leverages the evolutionary selection process to consolidate the functional arrangement of biological neurons within their networks. The initial goal involves the conversion of natural connectomes into artificial representations. The second objective centers on embedding the complex circuitry topology of artificial connectomes into both deep learning and deep reservoir networks, highlighting their neural-dynamic short-term and long-term memory and learning capabilities. Lastly, our third objective aims to establish structural explainability by examining the heterophilic/homophilic properties within the connectome and their impact on learning capabilities. In our study, the Elegans-AI models demonstrate superior performance compared to similar models that utilize either randomly rewired artificial connectomes or simulated bio-plausible ones. Notably, these Elegans-AI models achieve a top-1 accuracy of 99.99% on both Cifar10 and Cifar100, and 99.84% on MNIST Unsup. They do this with significantly fewer learning parameters, particularly when reservoir configurations of the connectome are used. Our findings indicate a clear connection between bio-plausible network patterns, the small-world characteristic, and learning outcomes, emphasizing the significant role of evolutionary optimization in shaping the topology of artificial neural networks for improved learning performance.

Elegans-AI: How the connectome of a living organism could model artificial neural networks / Bardozzo, F.; Terlizzi, A.; Simoncini, C.; Lio, P.; Tagliaferri, R.. - In: NEUROCOMPUTING. - ISSN 0925-2312. - 584:(2024). [10.1016/j.neucom.2024.127598]

Elegans-AI: How the connectome of a living organism could model artificial neural networks

Lio P.;
2024

Abstract

This paper introduces Elegans-AI models, a class of neural networks that leverage the connectome topology of the Caenorhabditis elegans to design deep and reservoir architectures. Utilizing deep learning models inspired by the connectome, this paper leverages the evolutionary selection process to consolidate the functional arrangement of biological neurons within their networks. The initial goal involves the conversion of natural connectomes into artificial representations. The second objective centers on embedding the complex circuitry topology of artificial connectomes into both deep learning and deep reservoir networks, highlighting their neural-dynamic short-term and long-term memory and learning capabilities. Lastly, our third objective aims to establish structural explainability by examining the heterophilic/homophilic properties within the connectome and their impact on learning capabilities. In our study, the Elegans-AI models demonstrate superior performance compared to similar models that utilize either randomly rewired artificial connectomes or simulated bio-plausible ones. Notably, these Elegans-AI models achieve a top-1 accuracy of 99.99% on both Cifar10 and Cifar100, and 99.84% on MNIST Unsup. They do this with significantly fewer learning parameters, particularly when reservoir configurations of the connectome are used. Our findings indicate a clear connection between bio-plausible network patterns, the small-world characteristic, and learning outcomes, emphasizing the significant role of evolutionary optimization in shaping the topology of artificial neural networks for improved learning performance.
2024
Artificial connectomes; C.elegans connectome; Connectomic architectures; Deep connectomic networks; Deep neural network transformers; Echo-state transformers; Multi-dyadic motifs
01 Pubblicazione su rivista::01a Articolo in rivista
Elegans-AI: How the connectome of a living organism could model artificial neural networks / Bardozzo, F.; Terlizzi, A.; Simoncini, C.; Lio, P.; Tagliaferri, R.. - In: NEUROCOMPUTING. - ISSN 0925-2312. - 584:(2024). [10.1016/j.neucom.2024.127598]
File allegati a questo prodotto
File Dimensione Formato  
Bardozzo_Elegans-AI_2024.pdf

accesso aperto

Note: https://doi.org/10.1016/j.neucom.2024.127598
Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Creative commons
Dimensione 4 MB
Formato Adobe PDF
4 MB Adobe PDF

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1723989
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 1
social impact