An Online Incremental Learning Vector Quantization

Authors:
Ye Xu;Shen Furao;Osamu Hasegawa;Jinxi Zhao
Affiliations:
The State Key Laboratory for Novel Software Technology, Nanjing University,;The State Key Laboratory for Novel Software Technology, Nanjing University,;Imaging Science and Engineering Lab, Tokyo Institute of Technology,;The State Key Laboratory for Novel Software Technology, Nanjing University,
Venue:
PAKDD '09 Proceedings of the 13th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining
Year:
2009

Citing 6
Cited 0

Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
A Dynamic Approach to Learning Vector Quantization

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 4 - Volume 04
The Nearest Subclass Classifier: A Compromise between the Nearest Mean and Nearest Neighbor Classifier

IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning Vector Quantization with Training Data Selection

IEEE Transactions on Pattern Analysis and Machine Intelligence
An incremental network for on-line unsupervised classification and topology learning

Neural Networks
An enhanced self-organizing incremental neural network for online unsupervised learning

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

As described in this paper, we propose online incremental learning vector quantization (ILVQ) for supervised classification tasks. As a prototype-based classifier, ILVQ needs no prior knowledge of the number of prototypes in the network or their initial value, as do most current prototype-based algorithms. It adopts a threshold-based insertion scheme to determine the number of prototypes needed for each class dynamically according to the distribution of training data. In addition, this insertion policy insures the fulfillment of the incremental learning goal, including both between-class incremental learning and within-class incremental learning. A technique for removing useless prototypes is used to eliminate noise interrupting the input data. Unlike other LVQ-based methods, the learning result won't be affected by the sequence of input patterns that come into the ILVQ. Results of experiments described herein show that the proposed ILVQ can accommodate the non-stationary data environment and can provide good recognition performance and storage efficiency.