Why in different execution different performance comes in the Neural Network same program ?
1 view (last 30 days)
Show older comments
Why in different execution different performance comes in the Neural Network same program ?
0 Comments
Accepted Answer
Greg Heath
on 8 May 2015
The state of the RNG is different. Therefore the random initial weights and random trn/val/tst data divisions are different.
For examples of initializing the RNG so that runs can be duplicated try searching on
greg rng(4151941)
greg rng(0)
greg rng('default')
4 Comments
Greg Heath
on 14 May 2015
You wouldn't have to post your data for me to do your work if you had performed the searches I recommended.
More Answers (0)
See Also
Categories
Find more on Classification 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!