Why in different execution different performance comes in the Neural Network same program ?
1 Ansicht (letzte 30 Tage)
Ältere Kommentare anzeigen
Deep Gogoi
am 8 Mai 2015
Kommentiert: Greg Heath
am 14 Mai 2015
Why in different execution different performance comes in the Neural Network same program ?
0 Kommentare
Akzeptierte Antwort
Greg Heath
am 8 Mai 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 Kommentare
Greg Heath
am 14 Mai 2015
You wouldn't have to post your data for me to do your work if you had performed the searches I recommended.
Weitere Antworten (0)
Siehe auch
Kategorien
Mehr zu Classification finden Sie in Help Center und File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!