How to Automate Neural Net Based Learning

Authors:
Roland Linder;Siegfried J. Pöppl
Affiliations:
-;-
Venue:
MLDM '01 Proceedings of the Second International Workshop on Machine Learning and Data Mining in Pattern Recognition
Year:
2001

Citing 11
Cited 0

Occam's razor

Information Processing Letters
The cascade-correlation learning architecture

Advances in neural information processing systems 2
Original Contribution: Improving model selection by nonconvergent methods

Neural Networks
Automatic early stopping using cross validation: quantifying the criteria

Neural Networks
Fast Convergent Generalized Back-Propagation Algorithm with Constant Learning Rate

Neural Processing Letters
A fast, compact approximation of the exponential function

Neural Computation
Modeling with constructive backpropagation

Neural Networks
Effiicient BackProp

Neural Networks: Tricks of the Trade, this book is an outgrowth of a 1996 NIPS workshop
Constructive algorithms for structure learning in feedforward neural networks for regression problems

IEEE Transactions on Neural Networks
Asymptotic statistical theory of overtraining and cross-validation

IEEE Transactions on Neural Networks
Efficient classification for multiclass problems using modular neural networks

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.01

Visualization

Abstract

Although neural networks have many appealing properties, yet there is neither a systematic way how to set up the topology of a neural network nor how to determine its various learning parameters. Thus an expert is needed for fine tuning. If neural network applications should not be realisable only for publications but in real life, fine tuning must become unnecessary. In the present paper an approach is demonstrated fulfilling this demand. Moreover referring to six medical classification and approximation problems of the PROBEN1 benchmark collection this approach will be shown even to outperform fine tuned networks.