Towards robust model selection using estimation and approximation error bounds
COLT '96 Proceedings of the ninth annual conference on Computational learning theory
Prequential and Cross-Validated Regression Estimation
Machine Learning
Nonparametric Time Series Prediction Through Adaptive ModelSelection
Machine Learning
Algebraic geometrical methods for hierarchical learning machines
Neural Networks
Orthogonal RBF Neural Network Approximation
Neural Processing Letters
Neural ARX Models and PAC Learning
AI '00 Proceedings of the 13th Biennial Conference of the Canadian Society on Computational Studies of Intelligence: Advances in Artificial Intelligence
On learning multicategory classification with sample queries
Information and Computation
A Fixed-Distribution PAC Learning Theory for Neural FIR Models
Journal of Intelligent Information Systems
Theoretical Properties of Projection Based Multilayer Perceptrons with Functional Inputs
Neural Processing Letters
Algebraic Analysis for Nonidentifiable Learning Machines
Neural Computation
Almost Linear VC-Dimension Bounds for Piecewise Polynomial Networks
Neural Computation
Post Data Mining Analysis for Decision Support through Econometrics
Information-Knowledge-Systems Management
Rate of convergence in density estimation using neural networks
Neural Computation
Nonlinear Function Learning Using Radial Basis Function Networks: Convergence and Rates
ICAISC '08 Proceedings of the 9th international conference on Artificial Intelligence and Soft Computing
A novel fast Kolmogorov's spline complex network for pattern detection
WSEAS TRANSACTIONS on SYSTEMS
A novel fast Kolmogorov's spline complex network for pattern detection
SMO'08 Proceedings of the 8th conference on Simulation, modelling and optimization
Estimation of a regression function by maxima of minima of linear functions
IEEE Transactions on Information Theory
Hardenability prediction of gear steel in refining process
CCDC'09 Proceedings of the 21st annual international conference on Chinese control and decision conference
Multicriteria decision making (MCDM): a framework for research and applications
IEEE Computational Intelligence Magazine
Neural network architecture selection: can function complexity help?
Neural Processing Letters
Computational Optimization and Applications
Data mining using an adaptive HONN model with hyperbolic tangent neurons
PKAW'10 Proceedings of the 11th international conference on Knowledge management and acquisition for smart systems and services
An L2-boosting algorithm for estimation of a regression function
IEEE Transactions on Information Theory
Comparisons of single- and multiple-hidden-layer neural networks
ISNN'11 Proceedings of the 8th international conference on Advances in neural networks - Volume Part I
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
Selection of weights for sequential feed-forward neural networks: an experimental study
IWANN'05 Proceedings of the 8th international conference on Artificial Neural Networks: computational Intelligence and Bioinspired Systems
Weak conditions for shrinking multivariate nonparametric density estimators
Journal of Multivariate Analysis
Approximation and estimation bounds for free knot splines
Computers & Mathematics with Applications
| Hi-index | 0.12 |
For a common class of artificial neural networks, the mean integrated squared error between the estimated network and a target function f is shown to be bounded by O \left ( {{C^2_f}\over n}\right ) + O\left ({nd\over N}{\rm log}\ N\right), where n is the number of nodes, d is the input dimension of the function, N is the number of training observations, and Cf is the first absolute moment of the Fourier magnitude distribution of f. The two contributions to this total risk are the approximation error and the estimation error. Approximation error refers to the distance between the target function and the closest neural network function of a given architecture and estimation error refers to the distance between this ideal network function and an estimated network function. With n ˜ Cf(N/(dlog N))1/2 nodes, the order of the bound on the mean integrated squared error is optimized to be O(Cf((d/N)log N)1/2). The bound demonstrates surprisingly favorable properties of network estimation compared to traditional series and nonparametric curve estimation techniques in the case that d is moderately large. Similar bounds are obtained when the number of nodes n is not preselected as a function of Cf (which is generally not known a priori), but rather the number of nodes is optimized from the observed data by the use of a complexity regularization or minimum description length criterion. The analysis involves Fourier techniques for the approximation error, metric entropy considerations for the estimation error, and a calculation of the index of resolvability of minimum complexity estimation of the family of networks.