MATLAB: Unsupervised Learning Vector Quantization (LVQ)

clusteringlearning vector quantizationunsupervised learning

Hello,

Correct me if I am wrong, but matlab includes the LVQ1 and LVQ2 training algorithms for learning vector quantization neural networks.

These algorithms refer to supervised learning.

Is there a way to use the "generalised LVQ" which is an unsupervised learning algorithm? This algorithm does not involves "target classes".

Thank you very much.

Natasha

Best Answer

Kohonen's LVQs are supervised versions of SOM. His books provide the details.

help newsom

doc newsom

Hope this helps.

Greg

Related Solutions

MATLAB: Matlab code for Supervised SOM neural network

A net cannot be self-organizing if it is supervised. You should be looking for Learning Vector Quantization Nets

>> lookfor lvq

 nnd14lv1                       - NND4LV1 LVQ1 demonstration.
 nnd14lv2                       - NND4LV1 LVQ2 demonstration.
 initlvq                        - LVQ weight initialization function.
 learnlv1                       - LVQ1 weight learning function.
 learnlv2                       - LVQ 2.1 weight learning function.
 lvqnet                         - Learning vector quantization (LVQ) neural network.
 lvqoutputs                     - Define settings for LVQ outputs, without changing values.
 newlvq                         - Create a learning vector quantization network.
 nnt2lvq                        - Update NNT 2.0 learning vector quantization network.

Thank you for formally accepting my answer

Greg

MATLAB: How to train a feedfordward neural network with error weights

 Use the command window
 help mse
 doc mse

Hope this helps.

Thank you for formally accepting my answer

Greg

Best Answer

Related Solutions

MATLAB: Matlab code for Supervised SOM neural network

MATLAB: How to train a feedfordward neural network with error weights

Related Question