Algebraic Analysis for Nonidentifiable Learning Machines
- 1 April 2001
- journal article
- Published by MIT Press in Neural Computation
- Vol. 13 (4) , 899-933
- https://doi.org/10.1162/089976601300014402
Abstract
This article clarifies the relation between the learning curve and the algebraic geometrical structure of a nonidentifiable learning machine such as a multilayer neural network whose true parameter...Keywords
This publication has 25 references indexed in Scilit:
- On the problem of applying AIC to determine the structure of a layered feedforward neural networkPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Generalization Error of Linear Neural Networks in Unidentifiable CasesPublished by Springer Nature ,1999
- Testing in locally conic models, and application to mixture modelsESAIM: Probability and Statistics, 1997
- A Regularity Condition of the Information Matrix of a Multilayer Perceptron NetworkNeural Networks, 1996
- Approximation and estimation bounds for artificial neural networksMachine Learning, 1994
- A universal theorem on learning curvesNeural Networks, 1993
- Statistical Theory of Learning Curves under Entropic Loss CriterionNeural Computation, 1993
- Four Types of Learning CurvesNeural Computation, 1992
- A new look at the statistical model identificationIEEE Transactions on Automatic Control, 1974
- Resolution of Singularities and Division of DistributionsCommunications on Pure and Applied Mathematics, 1970