Why in different execution different performance comes in the Neural Network same program ?
显示 更早的评论
Why in different execution different performance comes in the Neural Network same program ?
采纳的回答
Greg Heath
2015-5-8
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 个评论
Deep Gogoi
2015-5-9
Greg Heath
2015-5-11
If you set the RNG to the same state before the 1st random number assignment, the runs will be duplicated.
Did you perform the 3 searches I recommended?
Deep Gogoi
2015-5-12
Greg Heath
2015-5-14
You wouldn't have to post your data for me to do your work if you had performed the searches I recommended.
更多回答（0 个）
类别
在 帮助中心 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!
Translated by 
