Fast structural learning of distance-based neural networks

Authors:
Naoki Tominga;Qiangfu Zhao
Affiliations:
System Intelligence Laboratory, The University of Aizu, Fukushima, Japan;System Intelligence Laboratory, The University of Aizu, Fukushima, Japan
Venue:
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Year:
2009

Citing 4
Cited 0

The ART of Adaptive Pattern Recognition by a Self-Organizing Neural Network

Computer
A Simple Algorithm for Nearest Neighbor Search in High Dimensions

IEEE Transactions on Pattern Analysis and Machine Intelligence
Inducing NNC-trees with the R4-rule

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Evolutionary learning of nearest-neighbor MLP

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

The R4-rule is a structural learning algorithm for obtaining the smallest or nearly smallest distance-based neural networks. However, the computational cost of the R4-rule is relatively high because the learning vector quantization (LVQ) algorithm is used iteratively. To reduce the cost of the R4- rule, we investigate two approaches in this paper. The first one is called attentional learning (AL) which tries to reduce the number of data used for learning. The second one is called distance preservation (DP), which tries to reduce the number of times for calculating the distances during learning. The efficiency of these two approaches as well as their combination is verified through experiments on several public databases.