2 papers
cond-mat.dis-nn2024
Arbitrage equilibrium and the emergence of universal microstructure in deep neural networks
Venkat Venkatasubramanian, N Sanjeevrajan, Manasi Khandekar +2
Despite the stunning progress recently in large-scale deep neural network applications, our understanding of their microstructure, 'energy' functions, and optimal design remains in…
cs.ET2023
Thermodynamic AI and the fluctuation frontier
Patrick J. Coles, Collin Szczepanski, Denis Melanson +3
Many Artificial Intelligence (AI) algorithms are inspired by physics and employ stochastic fluctuations. We connect these physics-inspired AI algorithms by unifying them under a si…