Physics Stack Exchange is a question and answer site for active researchers, academics and students of physics. It's 100% free.

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

From what I gather, a Boltzmann machine can be identified with a spin glass. Though I don't know the details yet (and would welcome any references within the last 5 years--not, e.g. MacKay, etc.), I also gather that a Restricted Boltzmann Machine (RBM) corresponds to a particular type of spin glass, and it is well known that spin glasses have multiple decoupled timescales associated with their dynamics. Now, it would be of great interest to me if the spin glass corresponding to an RBM turned out to have a single well-defined characteristic timescale associated to it that is independent (i.e., any other timescales exhibit the same scaling under time reparametrization). So: is this true? In other words:

Does a restricted Boltzmann machine correspond to a spin glass that has a single well-defined characteristic timescale?

(I will wait a while before doing so, but suspect this may be better asked at the theoretical physics site.)

share|cite|improve this question

migrated from Aug 14 '12 at 10:45

This question came from our site for people interested in statistics, machine learning, data analysis, data mining, and data visualization.

A brief look at the wikipedia article for spin glass makes me think that there might be a correspondence since both Boltzmann machines and spin glasses have the same energy function (Hamiltonian?) – Neil G Mar 26 '12 at 6:35
A similar problem is addressed here, which you might find helpful - relating spin-glasses to a multilayer neural network: – AruniRC Dec 13 '14 at 4:06

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Browse other questions tagged or ask your own question.