List of works - Carlo Baldassi

A Three-Threshold Learning Rule Approaches the Maximal Capacity of Recurrent Neural Networks ⬇️

scientific article published on 20 August 2015

Efficiency of quantum vs. classical annealing in nonconvex learning problems

scientific article published on 30 January 2018

Efficient supervised learning in networks with binary synapses

scholarly article

Fast and accurate multivariate Gaussian modeling of protein families: predicting residue contacts and protein-interaction partners ⬇️

scientific article

From statistical inference to a differential learning rule for stochastic neural networks

scholarly article by Luca Saglietti et al published 6 December 2018 in Interface Focus

Learning may need only a few bits of synaptic precision ⬇️

scientific article published on 27 May 2016

Learning through atypical phase transitions in overparameterized neural networks

scientific article published in 2022

Local entropy as a measure for sampling solutions in constraint satisfaction problems ⬇️

RNAs competing for microRNAs mutually influence their fluctuations in a highly non-linear microRNA-dependent manner in single cells ⬇️

scientific article published on 20 February 2017

Role of Synaptic Stochasticity in Training Low-Precision Neural Networks

scientific article published on 01 June 2018

Shape similarity, better than semantic membership, accounts for the structure of visual object representations in a population of monkey inferotemporal neurons

scientific article

Shaping the learning landscape in neural networks around wide flat minima

scientific article published on 23 December 2019

Simultaneous identification of specifically interacting paralogs and interprotein contacts by direct coupling analysis. ⬇️

scientific article

Statistical Physics and Network Optimization Problems

Subdominant Dense Clusters Allow for Simple Learning and High Computational Performance in Neural Networks with Discrete Synapses ⬇️

scientific article published on 18 September 2015

Theory and learning protocols for the material tempotron model

article

Unreasonable effectiveness of learning neural networks: From accessible states and robust ensembles to basic algorithmic schemes ⬇️

scientific article

List of works by Carlo Baldassi

A Three-Threshold Learning Rule Approaches the Maximal Capacity of Recurrent Neural Networks ⬇️

Efficiency of quantum vs. classical annealing in nonconvex learning problems

Efficient supervised learning in networks with binary synapses

Fast and accurate multivariate Gaussian modeling of protein families: predicting residue contacts and protein-interaction partners ⬇️

From statistical inference to a differential learning rule for stochastic neural networks

Learning may need only a few bits of synaptic precision ⬇️

Learning through atypical phase transitions in overparameterized neural networks

Local entropy as a measure for sampling solutions in constraint satisfaction problems ⬇️

RNAs competing for microRNAs mutually influence their fluctuations in a highly non-linear microRNA-dependent manner in single cells ⬇️

Role of Synaptic Stochasticity in Training Low-Precision Neural Networks

Shape similarity, better than semantic membership, accounts for the structure of visual object representations in a population of monkey inferotemporal neurons

Shaping the learning landscape in neural networks around wide flat minima

Simultaneous identification of specifically interacting paralogs and interprotein contacts by direct coupling analysis. ⬇️

Statistical Physics and Network Optimization Problems

Subdominant Dense Clusters Allow for Simple Learning and High Computational Performance in Neural Networks with Discrete Synapses ⬇️

Theory and learning protocols for the material tempotron model

Unreasonable effectiveness of learning neural networks: From accessible states and robust ensembles to basic algorithmic schemes ⬇️