Natural Gradient Works Efficiently in Learning
- S. Amari
- Computer ScienceNeural Computation
- 15 February 1998
The dynamical behavior of natural gradient online learning is analyzed and is proved to be Fisher efficient, implying that it has asymptotically the same performance as the optimal batch estimation of parameters.
Methods of information geometry
Dynamics of pattern formation in lateral-inhibition type neural fields
- S. Amari
- PhysicsBiological cybernetics
- 1 June 1977
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.
Nonnegative Matrix and Tensor Factorizations - Applications to Exploratory Multi-way Data Analysis and Blind Source Separation
This book provides a broad survey of models and efficient algorithms for Nonnegative Matrix Factorization (NMF). This includes NMFs various extensions and modifications, especially Nonnegative Tensor…
Adaptive Blind Signal and Image Processing - Learning Algorithms and Applications
This volume unifies and extends the theories of adaptive blind signal and image processing and provides practical and efficient algorithms for blind source separation, Independent, Principal, Minor Component Analysis, and Multichannel Blind Deconvolution (MBD) and Equalization.
Differential-geometrical methods in statistics
- S. Amari
Adaptive blind signal and image processing
Find the secret to improve the quality of life by reading this adaptive blind signal and image processing and make the words as your good value to your life.
A New Learning Algorithm for Blind Signal Separation
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.
Improving support vector machine classifiers by modifying kernel functions
Interpolating between Optimal Transport and MMD using Sinkhorn Divergences
- Jean Feydy, Thibault Séjourné, François-Xavier Vialard, S. Amari, A. Trouvé, G. Peyré
- Computer ScienceInternational Conference on Artificial…
- 18 October 2018
This paper studies the Sinkhorn Divergences, a family of geometric divergences that interpolates between MMD and OT, and provides theoretical guarantees for positivity, convexity and metrization of the convergence in law.