Nonlinear function approximation: Computing smooth solutions with an adaptive greedy algorithm
Journal of Approximation Theory
Geometrical multi-resolution network based on ridgelet frame
Signal Processing
Decoupled control using neural network-based sliding-mode controller for nonlinear systems
Expert Systems with Applications: An International Journal
Journal of Approximation Theory
Estimates of covering numbers of convex sets with slowly decaying orthogonal subsets
Discrete Applied Mathematics
Letters: Convex incremental extreme learning machine
Neurocomputing
Direct adaptive neural flight control system for an unstable unmanned aircraft
Applied Soft Computing
Automatica (Journal of IFAC)
Incremental constructive ridgelet neural network
Neurocomputing
Complexity of Gaussian-radial-basis networks approximating smooth functions
Journal of Complexity
Modeling nonlinear elastic behavior of reinforced soil using artificial neural networks
Applied Soft Computing
Approximation capabilities of multilayer fuzzy neural networks on the set of fuzzy-valued functions
Information Sciences: an International Journal
The approximation operators with sigmoidal functions
Computers & Mathematics with Applications
Another look at statistical learning theory and regularization
Neural Networks
Prediction of a Lorenz chaotic attractor using two-layer perceptron neural network
Applied Soft Computing
Design of local fuzzy models using evolutionary algorithms
Computational Statistics & Data Analysis
Learning a function from noisy samples at a finite sparse set of points
Journal of Approximation Theory
Simplifying Particle Swarm Optimization
Applied Soft Computing
An approximation by neural networkswith a fixed weight
Computers & Mathematics with Applications
Simultaneous greedy approximation in Banach spaces
Journal of Complexity
Learning with generalization capability by kernel methods of bounded complexity
Journal of Complexity
Weighted quadrature formulas and approximation by zonal function networks on the sphere
Journal of Complexity
Approximation with neural networks activated by ramp sigmoids
Journal of Approximation Theory
Multivariate sigmoidal neural network approximation
Neural Networks
Parametric identification of structured nonlinear systems
Automatica (Journal of IFAC)
The errors of simultaneous approximation of multivariate functions by neural networks
Computers & Mathematics with Applications
Essential rate for approximation by spherical neural networks
Neural Networks
Squared and absolute errors in optimal approximation of nonlinear systems
Automatica (Journal of IFAC)
Brief Intelligent optimal control of robotic manipulators using neural networks
Automatica (Journal of IFAC)
Stable adaptive neuro-control design via Lyapunov function derivative estimation
Automatica (Journal of IFAC)
Adaptive-critic based optimal neuro control synthesis for distributed parameter systems
Automatica (Journal of IFAC)
Stable hybrid control based on discrete-event automata and receding-horizon neural regulators
Automatica (Journal of IFAC)
Predictive neuro-control of uncertain systems: design and use of a neuro-optimizer
Automatica (Journal of IFAC)
Book review: Adaptive neural network control of robotic manipulators
Automatica (Journal of IFAC)
Set Membership identification of nonlinear systems
Automatica (Journal of IFAC)
The errors of approximation for feedforward neural networks in the Lp metric
Mathematical and Computer Modelling: An International Journal
Approximation of level continuous fuzzy-valued functions by multilayer regular fuzzy neural networks
Mathematical and Computer Modelling: An International Journal
Approximate models for nonlinear dynamical systems and their generalization properties
Mathematical and Computer Modelling: An International Journal
Short-term forecasting of traffic delays in highway construction zones using on-line approximators
Mathematical and Computer Modelling: An International Journal
Approximation properties of local bases assembled from neural network transfer functions
Mathematical and Computer Modelling: An International Journal
Suboptimal Solutions to Team Optimization Problems with Stochastic Information Structure
SIAM Journal on Optimization
Selection of activation functions in the last hidden layer of the multilayer perceptron
ICAISC'12 Proceedings of the 11th international conference on Artificial Intelligence and Soft Computing - Volume Part I
Selective weight update rule for hybrid neural network
ISNN'12 Proceedings of the 9th international conference on Advances in Neural Networks - Volume Part I
Flexible and Robust Patterning by Centralized Gene Networks
Fundamenta Informaticae - Watching the Daisies Grow: from Biology to Biomathematics and Bioinformatics — Alan Turing Centenary Special Issue
Semi-physical neural modeling for linear signal restoration
Neural Networks
Adaptive value function approximation for continuous-state stochastic dynamic programming
Computers and Operations Research
Approximation and estimation bounds for free knot splines
Computers & Mathematics with Applications
DCOB: Action space for reinforcement learning of high DoF robots
Autonomous Robots
Regularized vector field learning with sparse approximation for mismatch removal
Pattern Recognition
Generalization ability of fractional polynomial models
Neural Networks
Machine learning with operational costs
The Journal of Machine Learning Research
Neural network modeling of vector multivariable functions in ill-posed approximation problems
Journal of Computer and Systems Sciences International
Approximation and Estimation Bounds for Subsets of Reproducing Kernel Kreĭn Spaces
Neural Processing Letters
Hi-index | 754.86 |
Approximation properties of a class of artificial neural networks are established. It is shown that feedforward networks with one layer of sigmoidal nonlinearities achieve integrated squared error of order O (1/n), where n is the number of nodes. The approximated function is assumed to have a bound on the first moment of the magnitude distribution of the Fourier transform. The nonlinear parameters associated with the sigmoidal nodes, as well as the parameters of linear combination, are adjusted in the approximation. In contrast, it is shown that for series expansions with n terms, in which only the parameters of linear combination are adjusted, the integrated squared approximation error cannot be made smaller than order 1/n2d/ uniformly for functions satisfying the same smoothness assumption, where d is the dimension of the input to the function. For the class of functions examined, the approximation rate and the parsimony of the parameterization of the networks are shown to be advantageous in high-dimensional settings