Hardness Results for Neural Network Approximation Problems
- 19 November 1999
- book chapter
- Published by Springer Nature
Abstract
No abstract availableKeywords
This publication has 17 references indexed in Scilit:
- The Hardness of Approximate Optima in Lattices, Codes, and Systems of Linear EquationsJournal of Computer and System Sciences, 1997
- The computational intractability of training sigmoidal neural networksIEEE Transactions on Information Theory, 1997
- Robust Trainability of Single NeuronsJournal of Computer and System Sciences, 1995
- On the complexity of training neural networks with continuous activation functionsIEEE Transactions on Neural Networks, 1995
- Strong universal consistency of neural network classifiersIEEE Transactions on Information Theory, 1993
- Training a 3-node neural network is NP-completeNeural Networks, 1992
- Decision theoretic generalizations of the PAC model for neural net and other learning applicationsInformation and Computation, 1992
- On learning a union of half spacesJournal of Complexity, 1990
- How to construct random functionsJournal of the ACM, 1986
- The densest hemisphere problemTheoretical Computer Science, 1978