Journal
COMPUTER SIMULATIONS IN PHYSICS AND BEYOND (CSP2017)
Volume 955, Issue -, Pages -Publisher
IOP PUBLISHING LTD
DOI: 10.1088/1742-6596/955/1/012001
Keywords
-
Categories
Ask authors/readers for more resources
We present a brief introduction to the statistical mechanics approaches for the study of inverse problems in data science. We then provide concrete new results on inferring couplings from sampled configurations in systems characterized by an extensive number of stable attractors in the low temperature regime. We also show how these result are connected to the problem of learning with realistic weak signals in computational neuroscience. Our techniques and algorithms rely on advanced mean-field methods developed in the context of disordered systems.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available