The complexity of model classes, and smoothing noisy data

DOI10.1016/S0167-6911(98)00008-5zbMath0909.93076OpenAlexW2178158849MaRDI QIDQ1274410

Sanjeev R. Kulkarni, Bartlett, Peter L.

Publication date: 12 January 1999

Published in: Systems \& Control Letters (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/s0167-6911(98)00008-5

zbMATH Keywords

system identificationsmoothingcomputational learning theorycovering numberscomplexity of the model class

Mathematics Subject Classification ID

Estimation and detection in stochastic control theory (93E10) Data smoothing in stochastic control theory (93E14)

Related Items (1)

Nonparametric nonlinear regression using polynomial and neural approximators: a numerical comparison

Cites Work

• Decision theoretic generalizations of the PAC model for neural net and other learning applications
• Bounding the Vapnik-Chervonenkis dimension of concept classes parameterized by real numbers
• Universal approximation bounds for superpositions of a sigmoidal function
• Efficient agnostic learning of neural networks with bounded fan-in
• The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network
• Rates of convergence of nearest neighbor estimation under arbitrary sampling
• Sample complexity for learning recurrent perceptron mappings
• A note on metric dimension and feedback in discrete time
• Convergence of stochastic processes

This page was built for publication: The complexity of model classes, and smoothing noisy data