Approximation and Estimation Bounds for Artificial Neural Networks
Machine Learning - Special issue on computational learning theory
Even on finite test sets smaller nets may perform better
Neural Networks
Optimal Sizing of Feedforward Neural Networks: Case Studies
ANNES '95 Proceedings of the 2nd New Zealand Two-Stream International Conference on Artificial Neural Networks and Expert Systems
The Chebyshev-polynomials-based unified model neural networks forfunction approximation
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
An analytical framework for local feedforward networks
IEEE Transactions on Neural Networks
Approximation capability in C(R¯n) by multilayer feedforward networks and related problems
IEEE Transactions on Neural Networks
Machine learning: a review of classification and combining techniques
Artificial Intelligence Review
AIKED'09 Proceedings of the 8th WSEAS international conference on Artificial intelligence, knowledge engineering and data bases
Supervised Machine Learning: A Review of Classification Techniques
Proceedings of the 2007 conference on Emerging Artificial Intelligence Applications in Computer Engineering: Real Word AI Systems with Applications in eHealth, HCI, Information Retrieval and Pervasive Technologies
Neural network architecture selection: can function complexity help?
Neural Processing Letters
Extension of the generalization complexity measure to real valued input data sets
ISNN'10 Proceedings of the 7th international conference on Advances in Neural Networks - Volume Part I
Artificial Intelligence in Medicine
Hi-index | 0.00 |
This work concerns the selection of input-output pairs for improved training of multilayer perceptrons, in the context of approximation of univariate real functions. A criterion for the choice of the number of neurons in the hidden layer is also provided. The main idea is based on the fact that Chebyshev polynomials can provide approximations to bounded functions up to a prescribed tolerance, and, in turn, a polynomial of a certain order can be fitted with a three-layer perceptron with a prescribed number of hidden neurons. The results are applied to a sensor identification example.