Work

Fluctuation-Dissipation Theorem and Models of Learning

Year: 2005

Type: article

Abstract: 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). Based on the fluctuation-dissipation relation in statistical physics, we then discuss a different experimental setup that might be able to solve the problem.

Source: Neural Computation

DOI: 10.1162/0899766054322982

Author: Ilya Nemenman

Institutions: University of California, Santa Barbara, Kavli Institute for Theoretical Physics, Columbia University

Language: English

Topic: Neural Networks and Applications

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: National Science Foundation

Awards: Institute for Theoretical Physics, SGER: Developing Learning Theory for Genetic Network Inference