Unreasonable Effectiveness of Learning Neural Nets: Accessible States and Robust Ensembles

  title={Unreasonable Effectiveness of Learning Neural Nets: Accessible States and Robust Ensembles},
  author={Carlo Baldassi and Christian Borgs and Jennifer T. Chayes and Alessandro Ingrosso and Carlo Lucibello and Luca Saglietti and Riccardo Zecchina},
Carlo Baldassi, 2 Christian Borgs, Jennifer Chayes, Alessandro Ingrosso, 2 Carlo Lucibello, 2 Luca Saglietti, 2 and Riccardo Zecchina 2, 4 Dept. Applied Science and Technology, Politecnico di Torino, Corso Duca degli Abruzzi 24, I-10129 Torino, Italy Human Genetics Foundation-Torino, Via Nizza 52, I-10126 Torino, Italy Microsoft Research, Cambridge, MA, USA Collegio Carlo Alberto, Via Real Collegio 30, I-10024 Moncalieri, Italy 

From This Paper

Figures, tables, and topics from this paper.


Publications referenced by this paper.
Showing 1-10 of 31 references

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

Carlo Baldassi, Alessandro Ingrosso, Carlo Lucibello, Luca Saglietti, Riccardo Zecchina
Journal of Statistical Mechanics: Theory and Experiment, • 2016
View 4 Excerpts
Highly Influenced

Learning by message-passing in neural networks with material synapses

Alfredo Braunstein, Riccardo Zecchina
Phys. Rev. Lett., • 2006
View 8 Excerpts
Highly Influenced

Deep learning

Yoshua Bengio, Geoffrey Hinton
Nature • 2015