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

ArXi:2506.23546v2 Announce Type: replace-cross Fixed points of recurrent neural networks can be leveraged to and generate information. These fixed points can be captured by the Boltzmann-Gibbs measure, which leads to neural Langevin dynamics that can be used to find them 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.