Gradient descent learning in and out of equilibrium
Journal Article
·
· Physical Review E
Relations between the off thermal equilibrium dynamical process of on-line learning and the thermally equilibrated off-line learning are studied for potential gradient descent learning. The approach of Opper to study on-line Bayesian algorithms is used for potential based or maximum likelihood learning. We look at the on-line learning algorithm that best approximates the off-line algorithm in the sense of least Kullback-Leibler information loss. The closest on-line algorithm works by updating the weights along the gradient of an effective potential, which is different from the parent off-line potential. A few examples are analyzed and the origin of the potential annealing is discussed.
- Sponsoring Organization:
- (US)
- OSTI ID:
- 40203373
- Journal Information:
- Physical Review E, Vol. 63, Issue 6; Other Information: DOI: 10.1103/PhysRevE.63.061905; Othernumber: PLEEE8000063000006061905000001; 109105PRE; PBD: Jun 2001; ISSN 1063-651X
- Publisher:
- The American Physical Society
- Country of Publication:
- United States
- Language:
- English
Similar Records
Dynamic gradient descent learning algorithms for enhanced empirical modeling of power plants
Gradient-Descent-Based Learning Gain for Backstepping Controller and Disturbance Observer of Nonlinear Systems
Approximate Bayesian Model Inversion for PDEs with Heterogeneous and State-Dependent Coefficients
Conference
·
Fri Nov 01 00:00:00 EST 1991
· Transactions of the American Nuclear Society; (United States)
·
OSTI ID:40203373
Gradient-Descent-Based Learning Gain for Backstepping Controller and Disturbance Observer of Nonlinear Systems
Journal Article
·
Thu Jan 05 00:00:00 EST 2023
· IEEE Access
·
OSTI ID:40203373
+1 more
Approximate Bayesian Model Inversion for PDEs with Heterogeneous and State-Dependent Coefficients
Journal Article
·
Tue Oct 15 00:00:00 EDT 2019
· Journal of Computational Physics
·
OSTI ID:40203373