On approximate learning by multi-layered feedforward circuits

DOI10.1016/J.TCS.2005.09.008MaRDI QIDQ2581366zbMATH OpenOpenAlexFDO

Authors Bhaskar Dasgupta, Barbara Hammer

Publication date 10 January 2006

Published in Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.tcs.2005.09.008

zbMATH Keywords

ApproximationLoading problemNeural networksNP-hardness

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• scientific article; zbMATH DE number 2080455
• Approximation by neural networks and learning theory
• Multilayer feedforward networks are universal approximators
• Learning theory and approximation by neural networks
• Approximation properties of a multilayered feedforward artificial neural network
• scientific article; zbMATH DE number 1083116
• The learning problem of multi-layer neural networks
• Approximation by Fully Complex Multilayer Perceptrons
• scientific article; zbMATH DE number 1784875
• Approximation properties of some two-layer feedforward neural networks

Cites work

• Feedforward nets for interpolation and classification
• Finiteness results for sigmoidal “neural” networks
• Hardness results for neural network approximation problems
• scientific article; zbMATH DE number 192916 (Why is no real title available?)
• scientific article; zbMATH DE number 3511136 (Why is no real title available?)
• scientific article; zbMATH DE number 3639144 (Why is no real title available?)
• scientific article; zbMATH DE number 1322222 (Why is no real title available?)
• scientific article; zbMATH DE number 1330033 (Why is no real title available?)
• scientific article; zbMATH DE number 1332666 (Why is no real title available?)
• scientific article; zbMATH DE number 774000 (Why is no real title available?)
• scientific article; zbMATH DE number 774005 (Why is no real title available?)
• scientific article; zbMATH DE number 774006 (Why is no real title available?)
• scientific article; zbMATH DE number 930356 (Why is no real title available?)
• Introduction to algorithms
• On the complexity of polyhedral separability
• On the hardness of approximating minimization problems
• Optimization, approximation, and complexity classes
• Robust trainability of single neurons
• The complexity and approximability of finding maximum feasible subsystems of linear relations
• The computational intractability of training sigmoidal neural networks
• The hardness of approximate optima in lattices, codes, and systems of linear equations

Cited in

(7)

• Bounds on the learning capacity of some multi-layer networks
• Hardness results for neural network approximation problems
• Scalable learning method for feedforward neural networks using minimal-enclosing-ball approximation
• scientific article; zbMATH DE number 2080455 (Why is no real title available?)
• scientific article; zbMATH DE number 1928632 (Why is no real title available?)
• Computational limitations on training sigmoid neural networks
• Markov chain network training and conservation law approximations: Linking microscopic and macroscopic models for evolution

This page was built for publication: On approximate learning by multi-layered feedforward circuits

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2581366)