We study how to optimise the architecture of a Deep Neural Network by rearranging the neurons within the hidden layers. In order to do so, we follow a theoretical suggestion that comes from the thermodynamic properties of some Restricted Boltzmann machines (RBMs). Namely, for a suitable definition of temperature, we move the neurons towards colder areas of the network. We find that such a procedure, in the analysed cases, improves the robustness of the network respectively by 4.8%, 6% and 2.8% with respect to the default choice of neurons equidistribution, without changing the accuracy. The result has a particular relevance in AI applications to satellites where resources are limited.

Branchini, P., Contucci, P., Cormenier, S., Manzan, G. (2025). Architectural optimisation in deep neural networks. Tests of a theoretically inspired method. NPJ ARTIFICIAL INTELLIGENCE., 1(1), 1-8 [10.1038/s44387-025-00034-6].

Architectural optimisation in deep neural networks. Tests of a theoretically inspired method

Contucci P.;Manzan G.
2025

Abstract

We study how to optimise the architecture of a Deep Neural Network by rearranging the neurons within the hidden layers. In order to do so, we follow a theoretical suggestion that comes from the thermodynamic properties of some Restricted Boltzmann machines (RBMs). Namely, for a suitable definition of temperature, we move the neurons towards colder areas of the network. We find that such a procedure, in the analysed cases, improves the robustness of the network respectively by 4.8%, 6% and 2.8% with respect to the default choice of neurons equidistribution, without changing the accuracy. The result has a particular relevance in AI applications to satellites where resources are limited.
2025
Branchini, P., Contucci, P., Cormenier, S., Manzan, G. (2025). Architectural optimisation in deep neural networks. Tests of a theoretically inspired method. NPJ ARTIFICIAL INTELLIGENCE., 1(1), 1-8 [10.1038/s44387-025-00034-6].
Branchini, P.; Contucci, P.; Cormenier, S.; Manzan, G.
File in questo prodotto:
Eventuali allegati, non sono esposti

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/11585/1092351
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
  • OpenAlex ND
social impact