Volume 43, Number 6, September II 1998
|Page(s)||635 - 640|
|Published online||01 September 2002|
A general learning algorithm for solving optimization problems and its application to the spin glass problem
Department of Computational Science,
National University of Singapore, Singapore
Accepted: 21 July 1998
We propose a general learning algorithm for solving optimization problems, based on a simple strategy of trial and adaptation. The algorithm maintains a probability distribution of possible solutions (configurations), which is updated continuously in the learning process. As the probability distribution evolves, better and better solutions are shown to emerge. The performance of the algorithm is illustrated by the application to the problem of finding the ground state of the Ising spin glass. A simple theoretical understanding of the algorithm is also presented.
PACS: 07.05.Mh – Neural networks, fuzzy logic, artificial intelligence / 75.10.Nr – Spin-glass and other random models / 02.60.Pn – Numerical optimization
© EDP Sciences, 1998
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.