4 papers
Statistical Physics of Deep Neural Networks: Initialization toward Optimal Channels
Kangyu Weng, Aohua Cheng, Ziyang Zhang +2
In deep learning, neural networks serve as noisy channels between input data and its representation. This perspective naturally relates deep learning with the pursuit of constructi…
A unified theory of information transfer and causal relation
Yang Tian, Hedong Hou, Yaoyuan Wang +2
Information transfer between coupled stochastic dynamics, measured by transfer entropy and information flow, is suggested as a physical process underlying the causal relation of sy…
Self-organized critical dynamics of RNA virus evolution
Xiaofei Ge, Kaichao You, Zeren Tan +3
RNA virus (e.g., SARS-CoV-2) evolves in a complex manner. Studying RNA virus evolution is vital for understanding molecular evolution and medicine development. Scientists lack, how…
Fourier-domain transfer entropy spectrum
Yang Tian, Yaoyuan Wang, Ziyang Zhang +1
We propose the Fourier-domain transfer entropy spectrum, a novel generalization of transfer entropy, as a model-free metric of causality. For arbitrary systems, this approach syste…