Physics – Condensed Matter – Disordered Systems and Neural Networks
Scientific paper
2011-04-14
Phys. Rev. E 83, 056114 (2011)
Physics
Condensed Matter
Disordered Systems and Neural Networks
15 pages, 10 figures, to be published in Phys. Rev. E
Scientific paper
We discuss how inference can be performed when data are sampled from the non-ergodic phase of systems with multiple attractors. We take as model system the finite connectivity Hopfield model in the memory phase and suggest a cavity method approach to reconstruct the couplings when the data are separately sampled from few attractor states. We also show how the inference results can be converted into a learning protocol for neural networks in which patterns are presented through weak external fields. The protocol is simple and fully local, and is able to store patterns with a finite overlap with the input patterns without ever reaching a spin glass phase where all memories are lost.
Braunstein Alexander
Ramezanpour Abolfazl
Zecchina Riccardo
Zhang Pei-Pei
No associations
LandOfFree
Inference and learning in sparse systems with multiple states does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Inference and learning in sparse systems with multiple states, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Inference and learning in sparse systems with multiple states will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-166811