{"id":5495,"date":"2025-07-23T11:35:46","date_gmt":"2025-07-23T02:35:46","guid":{"rendered":"https:\/\/www.phys.s.u-tokyo.ac.jp\/en\/?p=5495"},"modified":"2025-07-23T11:35:46","modified_gmt":"2025-07-23T02:35:46","slug":"common-feature-between-forest-fires-and-neural-networks-reveals-the-universal-framework-underneath","status":"publish","type":"post","link":"https:\/\/www.phys.s.u-tokyo.ac.jp\/en\/news\/5495\/","title":{"rendered":"Common feature between forest fires and neural networks reveals the universal framework underneath"},"content":{"rendered":"
\n
\"\"<\/a><\/figure><\/div>\n\n\n

Specially Appointed Researcher Keiichi Tamai, Specially Appointed Associate Professor Tsuyoshi Okubo, and\u00a0Professor Synge Todo<\/a> of the Graduate School of Science at The University of Tokyo in collaboration Aisin Corporation find that scaling laws apply to deep neural networks exhibiting absorbing phase transitions.<\/p>\n\n\n\n

Researchers have demonstrated that universal scaling laws, which describe how the properties of a system change with size and scale, apply to deep neural networks that exhibit absorbing phase transition behavior, a phenomenon typically observed in physical systems. The discovery not only provides a framework describing deep neural networks but also helps predict their trainability or generalizability. The findings were published in the journal\u00a0Physical Review Research<\/em>.<\/p>\n\n\n\n

See below for more information.<\/p>\n\n\n\n