Natural Gradient Works Efficiently in Learning
- 1 February 1998
- journal article
- Published by MIT Press in Neural Computation
- Vol. 10 (2), 251-276
- https://doi.org/10.1162/089976698300017746
Abstract
MIT Press Journals is a mission-driven, not-for-profit scholarly publisher devoted to the widest dissemination of its content.Keywords
This publication has 19 references indexed in Scilit:
- Information Geometry of Estimating Functions in Semi-Parametric Statistical ModelsBernoulli, 1997
- Information geometryContemporary Mathematics, 1997
- An Information-Maximization Approach to Blind Separation and Blind DeconvolutionNeural Computation, 1995
- Local and Global Convergence of On-Line LearningPhysical Review Letters, 1995
- A universal theorem on learning curvesNeural Networks, 1993
- Statistical Theory of Learning Curves under Entropic Loss CriterionNeural Computation, 1993
- Information geometry of Boltzmann machinesIEEE Transactions on Neural Networks, 1992
- Differential geometry of a parametric family of invertible linear systems—Riemannian metric, dual affine connections, and divergenceTheory of Computing Systems, 1987
- The relation between information theory and the differential geometry approach to statisticsInformation Sciences, 1985
- Neural theory of association and concept-formationBiological Cybernetics, 1977