DOE OSTI · 21560287
Inference and learning in sparse systems with multiple states
Abstract
We discuss how inference can be performed when data are sampled from the nonergodic phase of systems with multiple attractors. We take as a 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.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Braunstein, A, Ramezanpour, A, Zhang, P, Zecchina, R. 2011-05-15. Inference and learning in sparse systems with multiple states. https://doi.org/10.1103/physreve.83.056114
Cite the original work for its findings. Save a collection to share your selection of sources.