How do I find the indices of the Self Organizing Map (SOM) training set output

I'm using the SOM toolbox and have created the following:
net = selforgmap([10 10)];
[net,tr] = train(net,inputs);
where 'inputs' is a 5x10000 matrix of 5 parameters with 10000 samples.
using plotsomhits(net,inputs); shows how the 10000 samples are getting clustered.
Question: How do I output where each individual vector is clustered? For example where on the 10x10 grid is vector #1 located?
TIA
Scott

 採用された回答

Shashank Prasanna
Shashank Prasanna 2013 年 8 月 5 日
編集済み: Shashank Prasanna 2013 年 8 月 5 日
Here is an example that should help you:
net = selforgmap([10 10]);
[net,tr] = train(net,inputs); % Classify input data
op_som = vec2ind(net(inputs))';
for each input in inputs, op_som will have a numbering between 1 to n based on which cluster it belongs to.

その他の回答 (2 件)

Scott
Scott 2013 年 8 月 6 日

0 投票

Works great, thanks Shashank! Scott

カテゴリ

ヘルプ センター および File ExchangeDeep Learning Toolbox についてさらに検索

質問済み:

2013 年 8 月 5 日

回答済み:

2020 年 8 月 25 日

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by