Virtually every organism gathers information about its noisy environment and builds models from that data, mostly using neural networks. Here, we use stochastic thermodynamics to analyse 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 $\eta\le1$. We discuss the conditions for optimal learning and analyse Hebbian learning in the thermodynamic limit.
Categories: cond-mat.stat-mech cond-mat.dis-nn physics.bio-ph