What is the reason for such low classification accuracy? How can I overcome this problem?
3 次查看(过去 30 天)
显示 更早的评论
For context, I am working with a dataset for diagnosing AD patients using their EEG recordings. Using a train test split on different epochs produced very high accuracy. However, when computing the train test split by subject, my validation accuracy is incredibly low. Do you have any suggestions for how I can overcome this problem?
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/938614/image.png)
0 个评论
回答(1 个)
yanqi liu
2022-3-24
yes,sir,may be it is overfitting,so add some batch normal or dropout in layers to retrain the model
0 个评论
另请参阅
类别
在 Help Center 和 File Exchange 中查找有关 EEG/MEG/ECoG 的更多信息
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!