no code implementations • 18 Mar 2024 • Koji Hashimoto, Yuji Hirono, Jun Maeda, Jojiro Totsuka-Yoshinaka
It has been proposed that random wide neural networks near Gaussian process are quantum field theories around Gaussian fixed points.
no code implementations • 4 Feb 2024 • Koji Hashimoto, Yuji Hirono, Akiyoshi Sannai
Understanding the inner workings of neural networks, including transformers, remains one of the most challenging puzzles in machine learning.
no code implementations • 3 Jul 2023 • Koji Hashimoto, Tomoya Naito, Hisashi Naito
We find that simple neural networks with ReLU activation generate polytopes as an approximation of a unit sphere in various dimensions.
no code implementations • 28 Mar 2017 • Koji Hashimoto, Keiju Murata, Ryosuke Yoshii
For the first two cases, OTOCs are periodic in time because of their commensurable energy spectra.
High Energy Physics - Theory Disordered Systems and Neural Networks Chaotic Dynamics Quantum Physics