Statistical Clustering.LVQ .*;

Learning Vector Quantization

You might have noticed that learning vector quantization is also covered in the Neural Network area of this site. The neural network version works a bit differently, utilizing a weight matrix and a lot of supervised learning.

The concept of Learning Vector Quantization differs a little from standard neural networks, and curiously exists somewhere between k-means and ART1. It shares similar qualities of both but manages to fit a niche all its own.

K-means and LVQ are alike such that both are based on statistical pattern recognition instead of neural networks.

Unlike ART1, LVQ can operate with continuous patterns, so it's not restricted to binary patterns. Of course, this is solved with ART2.

ART1 and LVQ are alike such that both can be designed to create clusters dynamically.


public void footer() {
About | Contact | Privacy Policy | Terms of Service | Site Map
Copyright© 2009-2012 John McCullock. All Rights Reserved.