Fluctuation-dissipation theorem and models of learning
| dc.creator | Nemenman, Ilya | |
| dc.date | 2004-02-12 | |
| dc.date | 2004-10-26 | |
| dc.date.accessioned | 2026-07-07T05:58:14Z | |
| dc.date.available | 2026-07-07T05:58:14Z | |
| dc.description | Advances in statistical learning theory have resulted in a multitude of different designs of learning machines. But which ones are implemented by brains and other biological information processors? We analyze how various abstract Bayesian learners perform on different data and argue that it is difficult to determine which learning-theoretic computation is performed by a particular organism using just its performance in learning a stationary target (learning curve). Basing on the fluctuation-dissipation relation in statistical physics, we then discuss a different experimental setup that might be able to solve the problem. | |
| dc.description | 23 pages, 1 figure; manuscript restructured following reviewers' suggestions; references added; misprints corrected | |
| dc.identifier | https://arxiv.org/abs/q-bio/0402029 | |
| dc.identifier | http://arxiv.org/abs/q-bio/0402029 | |
| dc.identifier | Neural Comp. 17 (9): 2006-2033 SEP 2005 | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/88281 | |
| dc.subject | Neurons and Cognition | |
| dc.subject | Machine Learning | |
| dc.subject | Adaptation and Self-Organizing Systems | |
| dc.subject | Data Analysis, Statistics and Probability | |
| dc.title | Fluctuation-dissipation theorem and models of learning | |
| dc.type | text |