S
Shun-ichi Amari
Researcher at RIKEN Brain Science Institute
Publications - 496
Citations - 43340
Shun-ichi Amari is an academic researcher from RIKEN Brain Science Institute. The author has contributed to research in topics: Artificial neural network & Information geometry. The author has an hindex of 90, co-authored 495 publications receiving 40383 citations. Previous affiliations of Shun-ichi Amari include University of the West of Scotland & Shimadzu Corp..
Papers
More filters
Journal ArticleDOI
Natural gradient works efficiently in learning
TL;DR: In this paper, the authors used information geometry to calculate the natural gradients in the parameter space of perceptrons, the space of matrices (for blind source separation), and the spaces of linear dynamical systems for blind source deconvolution, and proved that Fisher efficient online learning has asymptotically the same performance as the optimal batch estimation of parameters.
Proceedings Article
A New Learning Algorithm for Blind Signal Separation
TL;DR: A new on-line learning algorithm which minimizes a statistical dependency among outputs is derived for blind separation of mixed signals and has an equivariant property and is easily implemented on a neural network like model.
Book
Nonnegative Matrix and Tensor Factorizations: Applications to Exploratory Multi-way Data Analysis and Blind Source Separation
TL;DR: This book provides a broad survey of models and efficient algorithms for Nonnegative Matrix Factorization (NMF), including NMFs various extensions and modifications, especially Nonnegative Tensor Factorizations (NTF) and Nonnegative Tucker Decompositions (NTD).
Journal ArticleDOI
Dynamics of pattern formation in lateral-inhibition type neural fields
TL;DR: The dynamics of pattern formation is studied for lateral-inhibition type homogeneous neural fields with general connections and it is proved that there are five types of pattern dynamics.