#### Filter Results:

- Full text PDF available (4)

#### Publication Year

2015

2017

- This year (1)
- Last 5 years (5)
- Last 10 years (5)

#### Publication Type

#### Co-author

#### Journals and Conferences

#### Key Phrases

Learn More

- Carlo Baldassi, Christian Borgs, +4 authors Riccardo Zecchina
- Proceedings of the National Academy of Sciences…
- 2016

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)

- Carlo Baldassi, Alessandro Ingrosso, Carlo Lucibello, Luca Saglietti, Riccardo Zecchina
- Physical review letters
- 2015

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)

- Carlo Baldassi, Federica Gerace, Carlo Lucibello, Luca Saglietti, Riccardo Zecchina
- Physical review. E
- 2016

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)

- Carlo Baldassi, Christian Borgs, +4 authors Riccardo Zecchina
- ArXiv
- 2016

- Federica Gerace, Carlo Lucibello, +10 authors Carlo Baldassi
- 2017

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)

- ‹
- 1
- ›