Selective Learning for Multilayer Feedforward Neural Networks

Authors:
Andries Petrus Engelbrecht
Affiliations:
-
Venue:
IWANN '01 Proceedings of the 6th International Work-Conference on Artificial and Natural Neural Networks: Connectionist Models of Neurons, Learning Processes and Artificial Intelligence-Part I
Year:
2001

Citing 8
Cited 0

Back-propagation algorithm which varies the number of hidden units

Neural Networks
Optimal brain damage

Advances in neural information processing systems 2
Generalization by weight-elimination with application to forecasting

NIPS-3 Proceedings of the 1990 conference on Advances in neural information processing systems 3
Query by committee

COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
Information-based objective functions for active data selection

Neural Computation
Selective training of feedforward artificial neural networks using matrix perturbation theory

Neural Networks
Neural Network Exploration Using Optional Experiment Design

Neural Network Exploration Using Optional Experiment Design
A Formulation for Active Learning with Applications to Object Detection

A Formulation for Active Learning with Applications to Object Detection

Quantified Score

Hi-index	0.00

Visualization

Abstract

Selective learning is an active learning strategy where the neural network selects during training the most informative patterns. This paper investigates a selective learning strategy where the informativeness of a pattern is measured as the sensitivity of the network output to perturbations in that pattern. The sensitivity approach to selective learning is then compared with an error selection approach where pattern informativeness is defined as the approximation error.