We consider dense, associative neural-networks trained by a teacher (i.e., with supervision) and we investigate their computational capabilities analytically, via statistical-mechanics tools, and numerically, via Monte Carlo simulations. In particular, we obtain a phase diagram which summarizes their performance as a function of the control parameters (e.g., quality and quantity of the training dataset, network storage, noise), that is valid in the limit of large network-size and structureless datasets. We also numerically test the learning, storing and retrieval capabilities of these networks on structured datasets such as MNist and Fashion MNist. As technical remarks, on the analytic side, we extend Guerra's interpolation to tackle the non-Gaussian distributions involved in the post-synaptic potentials while, on the computational side, we insert Plefka's approximation in the Monte Carlo scheme, to speed up the evaluation of the synaptic tensors, overall obtaining a novel and broad approach to investigate supervised learning in neural networks, beyond the shallow limit.

Dense Hebbian neural networks : a replica symmetric picture of supervised learning

Giannotti, Fosca;
2023

Abstract

We consider dense, associative neural-networks trained by a teacher (i.e., with supervision) and we investigate their computational capabilities analytically, via statistical-mechanics tools, and numerically, via Monte Carlo simulations. In particular, we obtain a phase diagram which summarizes their performance as a function of the control parameters (e.g., quality and quantity of the training dataset, network storage, noise), that is valid in the limit of large network-size and structureless datasets. We also numerically test the learning, storing and retrieval capabilities of these networks on structured datasets such as MNist and Fashion MNist. As technical remarks, on the analytic side, we extend Guerra's interpolation to tackle the non-Gaussian distributions involved in the post-synaptic potentials while, on the computational side, we insert Plefka's approximation in the Monte Carlo scheme, to speed up the evaluation of the synaptic tensors, overall obtaining a novel and broad approach to investigate supervised learning in neural networks, beyond the shallow limit.
2023
Settore INF/01 - Informatica
Dense networks; Hebbian learning; spin glasses; intelligent systems; large dataset; quality control; statistical mechanics; supervised learning
   Future Artificial Intelligence Research
   FAIR
   MUR
   PNRR

   Stochastic Methods for Complex Systems
   MUR
   PRIN2017

   Statistical mechanics of Learning Machines
   MUR
   PRIN2022
File in questo prodotto:
File Dimensione Formato  
Dense Hebbian neural networks-supervised.pdf

accesso aperto

Tipologia: Submitted version (pre-print)
Licenza: Solo Lettura
Dimensione 1.63 MB
Formato Adobe PDF
1.63 MB Adobe PDF
Dense_Hebbian_neural_networks_Giannotti_supervised_learning.pdf

Accesso chiuso

Tipologia: Published version
Licenza: Non pubblico
Dimensione 2.15 MB
Formato Adobe PDF
2.15 MB Adobe PDF   Richiedi una copia

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/11384/137122
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? ND
social impact