Ikeda, Kazushi (Kyoto Univ.)

A Dually Flat Structure of Quasi-Additive Algorithms

Scheduled for presentation during the Regular Session "Neural Networks I" (TuP01), Tuesday, July 25, 2006, 15:45−16:10, Room B2

17th International Symposium on Mathematical Theory of Networks and Systems, July 24-28, 2006, Kyoto, Japan

This information is tentative and subject to change. Compiled on May 27, 2023

Abstract

Quasi-Additive (QA) algorithms are a kind of on-line learning algorithms having two parameter vectors: One is an accumulation of input vectors and the other is a weight vector for prediction associated with the former by a non-linear function. We show that the vectors have a dually-flat structure from the information-geometric point of view, which makes it easier to discuss the convergence properties.