Biophysics and Soft Matter Seminar

Stochastic Thermodynamics of Learning

Wednesday, 05 July 2017 12:00PM PDT
Print
 
Biophysics and Soft Matter Seminar
 
Avinash Kumar
SFU Physics
 
Stochastic Thermodynamics of Learning
 
Jul 05, 2017 at 12PM
 

Synopsis



S. Goldt and U. Seifert
Physical Review Letters 118, 010601 – Published 6 March 2017

 

Virtually every organism gathers information about its noisy environment and builds models from those data, mostly using neural networks. Here, we use stochastic thermodynamics to analyze the learning of a classification rule by a neural network. We show that the information acquired by the network is bounded by the thermodynamic cost of learning and introduce a learning efficiency η≤1. We discuss the conditions for optimal learning and analyze Hebbian learning in the thermodynamic limit.