Robust Formulations for Training Multilayer Perceptrons

Authors:
Tommi Kärkkäinen;Erkki Heikkola
Affiliations:
Department of Mathematical Information Technology, University of Jyväskylä, FIN-40014 University of Jyväskylä, Finland;Department of Mathematical Information Technology, University of Jyväskylä, FIN-40014 University of Jyväskylä, Finland
Venue:
Neural Computation
Year:
2004

Citing 15
Cited 3

Robust regression and outlier detection

Robust regression and outlier detection
Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence

Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence
Evolution and generalization of a single neurone: I. single-layer perceptron as seven statistical classifiers

Neural Networks
Evolution and generalization of a single neurone: II. complexity of statistical classifiers and sample size considerations

Neural Networks
Evolution and generalization of a single neurone. III.: primitive, regularized, standard, robust and minimax regressions

Neural Networks
Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
Machine Learning

Machine Learning
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
MLP in layer-wise form with applications to weight decay

Neural Computation
A Simple Trick for Estimating the Weight Decay Parameter

Neural Networks: Tricks of the Trade, this book is an outgrowth of a 1996 NIPS workshop
Early Stopping-But When?

Neural Networks: Tricks of the Trade, this book is an outgrowth of a 1996 NIPS workshop
Square Unit Augmented, Radially Extended, Multilayer Perceptrons

Neural Networks: Tricks of the Trade, this book is an outgrowth of a 1996 NIPS workshop
Second-Order Learning Algorithm with Squared Penalty Term

Neural Computation
The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network

IEEE Transactions on Information Theory
Robust error measure for supervised neural network learning with outliers

IEEE Transactions on Neural Networks

The Iterated Classification Game: A New Model of the Cultural Transmission of Language

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Ideas about a regularized MLP classifier by means of weight decay stepping

ICANNGA'09 Proceedings of the 9th international conference on Adaptive and natural computing algorithms
Neural prediction of product quality based on pilot paper machine process measurements

ICANNGA'11 Proceedings of the 10th international conference on Adaptive and natural computing algorithms - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

The connection between robust statistical estimates and nonsmooth optimization is established. Based on the resulting family of optimization problems, robust learning problem formulations with regularization-based control on the model complexity of the multilayer perceptron network are described and analyzed. Numerical experiments for simulated regression problems are conducted, and new strategies for determining the regularization coefficient are proposed and evaluated.