different result is obtained for the same input using self-organizing map

5 views (last 30 days)
I used Neural Network Toolbox to train a self-organizing map for a given data set. I found that each run gave me a quite different result, like different "sample hits map". How to understand this difference? I just followed the standard routine, like
net = selforgmap([8 8]);
net = train(net, testInput);

Answers (1)

Greg Heath
Greg Heath on 3 Mar 2012
Initialize the random number generator to the same intial state; otherwise the results will be different.
Hope this helps.
Greg
  1 Comment
Mahmoud ELKAFAFY
Mahmoud ELKAFAFY on 14 Oct 2019
But, if you change the initialization of random number generator (e.g., rng(7) instaed of rng(3) for insatance), you will still get different results.

Sign in to comment.

Categories

Find more on Sequence and Numeric Feature Data Workflows in Help Center and File Exchange

Community Treasure Hunt

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

Start Hunting!