特異モデル(非正則モデル) モデルのパラメータ空間上に広がる損失地形の幾何に注目 引用)Jesse Hoogland and Stan van Wingerden. You’re Measuring Model Complexity Wrong. https://www.lesswrong.com/posts/6g8cAftfQufLmFDYT/you-re-measuring-model-complexity-wrong, 2023.
パラメータ空間上でのベイズ更新のダイナミクス 特異モデル 正則モデル 引用)Jesse Hoogland, Alexander Gietelink Oldenziel, Daniel Murfet, Stan van Wingerden. Towards Developmental Interpretability. https://www.lesswrong.com/posts/TjaeCWvLZtEDAS5Ex/towards-developmental-interpretability, 2023. 引用2) Liam Carroll, Edmund Lau. Growth and Form in a Toy Model of Superposition. https://www.lesswrong.com/posts/jvGqQGDrYzZM4MyaN/growth-and-form-in-a-toy-model-of- superposition, 2023.
Jesse Hoogland, Stan van Wingerden, Zach Furman, Daniel Murfet. Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient, ICLR 2025.
Jesse Hoogland, Stan van Wingerden, Zach Furman, Daniel Murfet. Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient, ICLR 2025.
Begins • February 11th, 2025: Professor Tadahiro Taniguchi, delivered a presentation on CPC to Professor Karl Friston, the originator of the Free Energy Principle. Professor Friston offered enthusiastic praise to Professor Taniguchi. This marked the first major recognition from the Western theoretical neuroscience community. 3. 自由エネルギー原理の提唱者 Karl Friston 教授がCPCを激賞
15th, 2025: Collective Predictive Coding Hypothesis: Symbol Emergence as Decentralized Bayesian Inference (i.e., the paper on "the CPC hypothesis"), has been selected as one of the best papers (outstanding paper) of 2024 in Frontiers in Robotics and AI. 3. CPC理論の国際的な認知は広がりつつある