Search Results for author: Keiichi Tamai

Found 1 papers, 0 papers with code

Absorbing Phase Transitions in Artificial Deep Neural Networks

no code implementations5 Jul 2023 Keiichi Tamai, Tsuyoshi Okubo, Truong Vinh Truong Duy, Naotake Natori, Synge Todo

More specifically, we study the order-to-chaos transition in the fully-connected feedforward neural networks and the convolutional ones to show that (i) there is a well-defined transition from the ordered state to the chaotics state even for the finite networks, and (ii) difference in architecture is reflected in that of the universality class of the transition.

Cannot find the paper you are looking for? You can Submit a new open access paper.