Learning Vector Quantization

Learning Vector Quantization (LVQ)
This is a supervised version of vector quantization. Classes are predefined and we have a set of labelled data. The goal is to determine a set of prototypes the best represent each class.

Self-Organizing Maps and Learning Vector Quantization for Feature Sequences, Somervuo and Kohonen. 2004 (pdf)
Classification of Textual Documents using LVQ, Fahad and Sikander. 2007 (pdf)
[edit] External links ...

5.2.1 Learning Vector Quantization.
5.2.2 Counter-propagation Network.
5.2.3 Probabilistic Neural Network.
5.3 Networks for Data Association
5.4 Networks for Data Conceptualization
5.5 Networks for Data Filtering
5.5.1 Recirculation.

Kohonen, T. (1990). Improved versions of learning vector quantization. International Joint Conference on Neural Networks 1, 545-550. San Diego, CA.
Kolata, G. (1984). The proper display of data. Science, 226, 156-157.

More advanced algorithms related to k means are Expected Maximization (EM) algorithm especially Gaussian Mixture, Self-Organization Map (SOM) from Kohonen, Learning Vector Quantization (LVQ).

It should just group similar colors together. After some searching i came up with two different techniques. ‘Learning Vector Quantization' (LVQ) and ‘Self Organizing Maps' (SOM). I chose the latter because it can learn unsupervised.

has introduced several new concepts to neural computing: fundamental theories of distributed associative memory and optimal associative mappings, the learning subspace method, the self-organizing feature maps (SOMs), the learning vector quantization ...

See also: Artificial neural network, Neural network, Clustering, Classification, Artificial intelligence