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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yu, Zhendong, Huang, Weizhong, Huang, Haiping
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918076122923008
author Yu, Zhendong
Huang, Weizhong
Huang, Haiping
author_facet Yu, Zhendong
Huang, Weizhong
Huang, Haiping
contents Fixed points of recurrent neural networks can be leveraged to store and generate information. These fixed points can be captured by the Boltzmann-Gibbs measure, which leads to neural Langevin dynamics that can be used for sampling and learning a real dataset. We call this type of generative model neural Langevin machine, which is interpretable due to its analytic form of distribution and is simple to train. Moreover, the learning process is derived as a local asymmetric plasticity rule, bearing biological relevance. Therefore, one can realize a continuous sampling of creative dynamics in a neural network, mimicking an imagination process in brain circuits. This neural Langevin machine may be another promising generative model, at least in its strength in circuit-based sampling and biologically plausible learning rule.
format Preprint
id arxiv_https___arxiv_org_abs_2506_23546
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neural Langevin Machine: a local asymmetric learning rule can be creative
Yu, Zhendong
Huang, Weizhong
Huang, Haiping
Neurons and Cognition
Disordered Systems and Neural Networks
Machine Learning
Neural and Evolutionary Computing
Fixed points of recurrent neural networks can be leveraged to store and generate information. These fixed points can be captured by the Boltzmann-Gibbs measure, which leads to neural Langevin dynamics that can be used for sampling and learning a real dataset. We call this type of generative model neural Langevin machine, which is interpretable due to its analytic form of distribution and is simple to train. Moreover, the learning process is derived as a local asymmetric plasticity rule, bearing biological relevance. Therefore, one can realize a continuous sampling of creative dynamics in a neural network, mimicking an imagination process in brain circuits. This neural Langevin machine may be another promising generative model, at least in its strength in circuit-based sampling and biologically plausible learning rule.
title Neural Langevin Machine: a local asymmetric learning rule can be creative
topic Neurons and Cognition
Disordered Systems and Neural Networks
Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2506.23546