Vytautas Vysniauskas, Frans C.A. Groen, Ben J.A. Kröse  Home/Search
Context
Related
| wins.uva.nl/pub/co...VysGroKro93b.ps.gz wins.uva.nl/pub/co...VysGroKro93b.ps.gz Cached: PS.gz PS PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
Image Update HelpPS.gz PS PDF From: wins.uva.nl/resear...publications (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: This paper presents a methodology to estimate the optimal number of learning samples and the number of hidden units needed to obtain a desired accuracy of a function approximation by a feedforward network. The representation error and the generalization error, components of the total approximation error are analyzed and the approximation accuracy of a feedforward network is investigated as a function of the number of hidden units and the number of learning samples. Based on the asymptotical... (Update)
Active bibliography (related documents): More All
0.5: Minimisation Methods for Training Feed-Forward Neural Networks - van der Smagt (1992) (Correct)
0.5: VC Dimension and Learnability of Sparse Polynomials and.. - Karpinski, Werther (1989) (Correct)
0.1: A Real-Time Learning Neural Robot Controller - van der Smagt, Kröse (1991) (Correct)
Similar documents based on text: More All
0.4: Orthogonal Incremental Learning of a Feedforward Network - Vysniauskas, Groen, Kröse (1995) (Correct)
0.3: Multiplier-Free Feedforward Networks - Khan (Correct)
0.3: Capacity of Structured Multilayer Networks with Shared Weights - Kröner, Moratz (Correct)
BibTeX entry: (Update)
@misc{ vysniauskas-optimal,
author = "Vytautas Vysniauskas and Frans C.A. Groen and Ben J.A. Kröse",
title = "The Optimal Number of Learning Samples and Hidden Units in Function Approximation
With a Feedforward Network",
url = "citeseer.ist.psu.edu/vysniauskas93optimal.html" }
Citations (may not include all citations):1527 Optimization by Simulated Annealing - Kirkpatrick, Gelatt et al. - 1983
623 Multilayer Feedforward Networks are Universal Approximators (context) - Hornik, Stinchcombe et al. - 1989
454 the uniform convergence of relative frequencies of events to.. (context) - Vapnik, Chervonenkis et al. - 1971
357 Approximation by Superpositions of a Sigmoidal Function (context) - Cybenko - 1989
348 Estimation of dependences based on empirical data (context) - Vapnik - 1982
340 Learning representation by back--propagating errors (context) - Rumelhart, Hinton et al. - 1986
235 the Approximate Realization of Continuous Mappings by Neural.. (context) - Funahashi - 1989
139 Stochastic complexity and modeling (context) - Rissanen - 1986
99 Learning in Artificial Neural Networks: A Statistical Perspe.. (context) - White - 1989
89 Approximation and estimation bounds for artificial neural ne.. (context) - Barron - 1991
85 Simplifying Neural Networks by Soft WeightSharing (context) - Nowlan, Hinton - 1992
64 Connectionist Nonparametric Regression: Multilayer Feedforwa.. (context) - White - 1990
63 What Size Net Gives Valid Generalization (context) - Baum, Haussler - 1989
58 Statistical mechanics of learning from examples (context) - Seung, Sompolinsky et al. - 1992
47 Complexity Regularization with Application to Neural Network.. (context) - Barron - 1991
44 A Statistical Approach to Learning and Generalization in Lay.. (context) - Levin, Thishby et al. - 1990
39 Restart procedures for the conjugate gradient method (context) - Powell - 1977
17 A New Approach for Finding the Global Minimum of Error Funct.. (context) - Baba - 1989
9 Learning strategies for a vision based neural controller for.. (context) - Krose, van der Korst et al. - 1990
2 the Geometry of Feedforward Neural Network Weight Spaces (context) - Chen, Hecht-Nielsen et al. - 1991
2 Generalizing the PAC Model: Sample Size Bounds From Metric D.. (context) - Hausler - 1989
1 A one layer feedback, artificial network with a Bayesian lea.. (context) - Lansen, Ekeberg - 1989
1 Control of the UvA OSCAR-6 robot (context) - van der Smagt - 1991
Documents on the same site (http://www.wins.uva.nl/research/ias/publications/publications.html): More
Observer Curve and Object Detection from the Optic Flow - Dev, Kröse, Dorst, Groen (Correct)
Recovering Patch Parameters from the Optic Flow with Auto.. - Dev, Kröse, Groen (Correct)
Interpolative Robot Control With The Nested Network Approach - van der Smagt, Jansen.. (1992) (Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC