Including metric space topology in neural networks training by ordering patterns

Authors:
Cezary Dendek;Jacek Mańdziuk
Affiliations:
Faculty of Mathematics and Information Science, Warsaw University of Technology, Warsaw, Poland;Faculty of Mathematics and Information Science, Warsaw University of Technology, Warsaw, Poland
Venue:
ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part II
Year:
2006

Citing 3
Cited 2

Incremental class learning approach and its application to handwritten digit recognition

Information Sciences—Informatics and Computer Science: An International Journal
Combining RBF Networks Trained by Different Clustering Techniques

Neural Processing Letters
Recognition of Cursive Roman Handwriting - Past, Present and Future

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1

Improving Performance of a Binary Classifier by Training Set Selection

ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I
Probability-Based Distance Function for Distance-Based Classifiers

ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper a new approach to the problem of ordering data in neural network training is presented. According to conducted research, generalization error visibly depends on the order of the training examples. Construction of an order gives some possibility to incorporate knowledge about structure of input and output space into the training process. Simulation results conducted for the isolated handwritten digit recognition problem confirmed the above claims.