Physics – Condensed Matter – Disordered Systems and Neural Networks
Scientific paper
1997-12-15
Physica A 257 (1998) 28-35
Physics
Condensed Matter
Disordered Systems and Neural Networks
5 pages, 1 figure, to appear in Physica A
Scientific paper
10.1016/S0378-4371(98)00126-5
We study the problem of determining the Hamiltonian of a fully connected Ising Spin Glass of $N$ units from a set of measurements, whose sizes needs to be ${\cal O}(N^2)$ bits. The student-teacher scenario, used to study learning in feed-forward neural networks, is here extended to spin systems with arbitrary couplings. The set of measurements consists of data about the local minima of the rugged energy landscape. We compare simulations and analytical approximations for the resulting learning curves obtained by using different algorithms.
Caticha Nestor
Kinouchi Osame
Kuva Silvia
No associations
LandOfFree
Learning a spin glass: determining Hamiltonians from metastable 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 Learning a spin glass: determining Hamiltonians from metastable states, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Learning a spin glass: determining Hamiltonians from metastable states will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-156672