Part 2: Multilayer perceptron and natural gradient learning
Author:
- 1 March 2006
- journal article
- Published by Springer Nature in New Generation Computing
- Vol. 24 (1) , 79-95
Abstract
No abstract availableKeywords
This publication has 17 references indexed in Scilit:
- Dynamics of the adaptive natural gradient descent method for soft committee machinesPhysical Review E, 2004
- Online learning dynamics of multilayer perceptrons with unidentifiable parametersJournal of Physics A: General Physics, 2003
- Likelihood ratio of unidentifiable models and multilayer neural networksThe Annals of Statistics, 2003
- On-Line Learning Theory of Soft Committee Machines with Correlated Hidden Units –Steepest Gradient Descent and Natural Gradient Descent–Journal of the Physical Society of Japan, 2003
- On the Problem in Model Selection of Neural Network Regression in Overrealizable ScenarioNeural Computation, 2002
- Adaptive natural gradient learning algorithms for various stochastic modelsNeural Networks, 2000
- Adaptive Method of Realizing Natural Gradient Learning for Multilayer PerceptronsNeural Computation, 2000
- Local minima and plateaus in hierarchical structures of multilayer perceptronsNeural Networks, 2000
- Natural Gradient Works Efficiently in LearningNeural Computation, 1998
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989