How can I choose the best neural network in MATLAB when my results change each time I retrain?

3 次查看（过去 30 天）
ampaul
ampaul 2017-6-15
编辑： KJVKU999 2017-6-15
Hi. I have finally built a dataset and trained it (for classification) in both patternnet and the Classification Learner App. I usually get an accuracy of over 98%, but each time I retrain the network, this number changes. How do I know which network is the best when each of them vary around 1% each time I retrain? Thanks

请先登录，再回答此问题。

回答（1 个）

KJVKU999
KJVKU999 2017-6-15
编辑：KJVKU999 2017-6-15
You can use at the beginning of your program:
rng(1);
so that your results won't differ every time you retrain your network.
This link will provide more information: https://www.mathworks.com/help/matlab/ref/rng.html

类别

在 Help Center 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息

标签

Community Treasure Hunt

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

Start Hunting!

Translated by