Luca Saglietti

Learn More
We show that discrete synaptic weights can be efficiently used for learning in large scale neural systems, and lead to unanticipated computational performance. We focus on the representative case of learning random patterns with binary synapses in single layer networks. The standard statistical analysis shows that this problem is exponentially dominated by(More)
In artificial neural networks, learning from data is a computationally demanding task in which a large number of connection weights are iteratively tuned through stochastic-gradient-based heuristic processes over a cost function. It is not well understood how learning occurs in these systems, in particular how they avoid getting trapped in configurations(More)
Learning in neural networks poses peculiar challenges when using discretized rather then continuous synaptic states. The choice of discrete synapses is motivated by biological reasoning and experiments, and possibly by hardware implementation considerations as well. In this paper we extend a previous large deviations analysis which unveiled the existence of(More)
We study the problem of stochastic optimization for deep learning in the parallel computing environment under communication constraints. A new algorithm is proposed in this setting where the communication and coordination of work among concurrent processes (local workers), is based on an elastic force which links the parameters they compute with a center(More)
Carlo Baldassi,1, 2, 3 Federica Gerace,2, 4 Hilbert J. Kappen,5 Carlo Lucibello,2, 4 Luca Saglietti,2, 4 Enzo Tartaglione,2, 4 and Riccardo Zecchina1, 2, 6 Bocconi Institute for Data Science and Analytics, Bocconi University, Milano, Italy Italian Institute for Genomic Medicine, Torino, Italy Istituto Nazionale di Fisica Nucleare, Sezione di Torino, Italy(More)
We report on the microwave properties of coaxial cavities built by using bulk MgB2 superconductor prepared by reactive liquid Mg infiltration technology. We have assembled a homogeneous cavity by using an outer MgB2 cylinder and an inner MgB2 rod and a hybrid cavity by using an outer copper cylinder and the same MgB2 rod as inner conductor. By the analysis(More)
  • 1