Neural Langevin Machine: a local asymmetric learning rule can be creative

Abstract:Fixed points of recurrent neural networks can be leveraged to store and generate information. These fixed points are captured by the Boltzmann-Gibbs measure, which leads to neural Langevin dynamics that relax to those fixed points for generative learning of a real dataset. We call this type of generative model a neural Langevin machine, which derives an asymmetric and firing-rate-speed-adjusted learning rule requiring only local neural signals, thereby bearing biological relevance in terms of local predictive learning. An out-of-equilibrium regime of the generative process is revealed, together with a memorization-to-generalization transition with increasing training data size. The neuro-inspired machine can also realize a continuous exploration of the phase space for different kinds of generative images and can denoise a corrupted image as well.

Neurons and Cognition (q-bio.NC); Disordered Systems and Neural Networks (cond-mat.dis-nn); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE)

arXiv:2506.23546 [q-bio.NC]

(or arXiv:2506.23546v3 [q-bio.NC] for this version)