Biophysics Journal Club

Stochastic Thermodynamics of Learning

Wed, 05 Jul 2017 1:00 PM
Print

Biophysics Journal Club
Stochastic Thermodynamics of Learning

Avinash Kumar
Department of Physics, SFU

July 5, 2017 at 1:00pm in P8445.2

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.