The statistical mechanics of learning a rule
Journal Article
·
· Reviews of Modern Physics; (United States)
- Department of Physics, University of Oxford, Oxford OX1 3NP (United Kingdom)
- Physikalisches Institut, Julius-Maximilians-Universitaet, Am Hubland, D-8700 Wuerzburg (Germany)
A summary is presented of the statistical mechanical theory of learning a rule with a neural network, a rapidly advancing area which is closely related to other inverse problems frequently encountered by physicists. By emphasizing the relationship between neural networks and strongly interacting physical systems, such as spin glasses, the authors show how learning theory has provided a workshop in which to develop new, exact analytical techniques.
- OSTI ID:
- 6647513
- Journal Information:
- Reviews of Modern Physics; (United States), Vol. 65:2; ISSN 0034-6861
- Country of Publication:
- United States
- Language:
- English
Similar Records
Machine Learning Accelerates the Discovery of Design Rules and Exceptions in Stable Metal–Oxo Intermediate Formation
Navigating Transition-Metal Chemical Space: Artificial Intelligence for First-Principles Design
Statistically-informed deep learning for gravitational wave parameter estimation
Journal Article
·
Tue Jul 23 00:00:00 EDT 2019
· ACS Catalysis
·
OSTI ID:6647513
+3 more
Navigating Transition-Metal Chemical Space: Artificial Intelligence for First-Principles Design
Journal Article
·
Fri Jan 22 00:00:00 EST 2021
· Accounts of Chemical Research
·
OSTI ID:6647513
+2 more
Statistically-informed deep learning for gravitational wave parameter estimation
Journal Article
·
Tue Nov 30 00:00:00 EST 2021
· Machine Learning: Science and Technology
·
OSTI ID:6647513
+2 more