3 papers
q-bio.NC2026
Neural Langevin Machine: a local asymmetric learning rule can be creative
Zhendong Yu, Weizhong Huang, Haiping Huang
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 neur…
q-bio.NC2025
Network reconstruction may not mean dynamics prediction
Zhendong Yu, Haiping Huang
With an increasing amount of observations on the dynamics of many complex systems, it is required to reveal the underlying mechanisms behind these complex dynamics, which is fundam…
cond-mat.stat-mech2024
Nonequilbrium physics of generative diffusion models
Zhendong Yu, Haiping Huang
Generative diffusion models apply the concept of Langevin dynamics in physics to machine leaning, attracting a lot of interests from engineering, statistics and physics, but a comp…