24 citations · 25 across the 2 of their papers we have counts for
3 papers
cond-mat.dis-nn2023★ 1 cited
Training neural networks with structured noise improves classification and generalization
Marco Benedetti, Enrico Ventura
The beneficial role of noise-injection in learning is a consolidated concept in the field of artificial neural networks, suggesting that even biological systems might take advantag…
cond-mat.dis-nn2022★ 24 cited
Supervised perceptron learning vs unsupervised Hebbian unlearning: Approaching optimal memory retrieval in Hopfield-like networks
Marco Benedetti, Enrico Ventura, Enzo Marinari +2
The Hebbian unlearning algorithm, i.e. an unsupervised local procedure used to improve the retrieval properties in Hopfield-like neural networks, is numerically compared to a super…
cond-mat.dis-nn2021
Recognition Capabilities of a Hopfield Model with Auxiliary Hidden Neurons
Marco Benedetti, Victor Dotsenko, Giulia Fischetti +2
We study the recognition capabilities of the Hopfield model with auxiliary hidden layers, which emerge naturally upon a Hubbard-Stratonovich transformation. We show that the recogn…