Active Learning Using a Constructive Neural Network Algorithm

Authors:
José Luis Subirats;Leonardo Franco;Ignacio Molina Conde;José M. Jerez
Affiliations:
Departamento de Lenguajes y Ciencias de la Computación Escuela Técnica Superior de Ingeniería en Informática, Universidad de Málaga, Málaga, Spain 29071;Departamento de Lenguajes y Ciencias de la Computación Escuela Técnica Superior de Ingeniería en Informática, Universidad de Málaga, Málaga, Spain 29071;Departamento de Tecnología Electrónica Escuela Técnica Superior de Ingeniería en Telecomunicación, Universidad de Málaga, Málaga, Spain 29071;Departamento de Lenguajes y Ciencias de la Computación Escuela Técnica Superior de Ingeniería en Informática, Universidad de Málaga, Málaga, Spain 29071
Venue:
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part II
Year:
2008

Citing 11
Cited 0

The upstart algorithm: a method for constructing and training feedforward neural networks

Neural Computation
Neural network constructive algorithms: trading generalization for learning efficiency?

Circuits, Systems, and Signal Processing - Special issue: networks for neural processing
Pedagogical pattern selection strategies

Neural Networks
Improving Generalization with Active Learning

Machine Learning - Special issue on structured connectionist systems
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Pre-pruning Classification Trees to Reduce Overfitting in Noisy Domains

IDEAL '02 Proceedings of the Third International Conference on Intelligent Data Engineering and Automated Learning
Class Noise vs. Attribute Noise: A Quantitative Study

Artificial Intelligence Review
Pruning Training Sets for Learning of Object Categories

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Generalization and Selection of Examples in Feedforward Neural Networks

Neural Computation
An empirical evaluation of constructive neural network algorithms in classification tasks

International Journal of Innovative Computing and Applications
Neural network architecture selection: size depends on function complexity

ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

Constructive neural network algorithms suffer severely from overfitting noisy datasets as, in general, they learn the set of examples until zero error is achieved. We introduce in this work a method for detect and filter noisy examples using a recently proposed constructive neural network algorithm. The method works by exploiting the fact that noisy examples are harder to be learnt, needing a larger number of synaptic weight modifications than normal examples. Different tests are carried out, both with controlled experiments and real benchmark datasets, showing the effectiveness of the approach.