Vapnik-Chervonenkis dimension of recurrent neural networks

DOI10.1016/S0166-218X(98)00014-6zbMath0907.68156OpenAlexW2053955420MaRDI QIDQ1265745

Pascal Koiran

Publication date: 15 December 1998

Published in: Discrete Applied Mathematics (Search for Journal in Brave)

Full work available at URL: http://www.elsevier.com/locate/dam

zbMATH Keywords

neural networksVapnik-Chervonenkis dimensionfeedforward networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (5)

Complete controllability of continuous-time recurrent neural networks ⋮ On the Complexity of Computing and Learning with Multiplicative Neural Networks ⋮ A learning result for continuous-time recurrent neural networks ⋮ Unnamed Item ⋮ Compressive sensing and neural networks from a statistical learning perspective

Cites Work

• Unnamed Item
• Polynomial bounds for VC dimension of sigmoidal and general Pfaffian neural networks
• Neural networks with quadratic VC dimension
• Feedforward nets for interpolation and classification
• Analog computation via neural networks
• On the computational power of neural nets
• Bounding the Vapnik-Chervonenkis dimension of concept classes parameterized by real numbers
• Learnability and the Vapnik-Chervonenkis dimension
• Sample complexity for learning recurrent perceptron mappings
• Neural networks and physical systems with emergent collective computational abilities.

This page was built for publication: Vapnik-Chervonenkis dimension of recurrent neural networks