What to do when training doesn't fit training data well?
11 vues (au cours des 30 derniers jours)
Afficher commentaires plus anciens
Hello,
I've been working on a Deep Learning system to learn some simple communication system properties and I'm having trouble with training/predicting. First, the training process quickly goes to zero, which would indicate that it has fit the data well, or even overfit the training data.
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/304831/image.png)
However, when using the predict function on the training data to double check, the plot indicates that the network does not predict the data well:
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/304835/image.jpeg)
And cross validation prediction is even worse:
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/304839/image.jpeg)
Does anyone have a guess as to why the training process shows an error close to zero, but both training set and cv set prediction is poor?
Thanks!
3 commentaires
vaibhav mishra
le 30 Juin 2020
maybe your model is getting overfit.
try to adopt some dropout and regularization in your model.
Réponses (2)
vaibhav mishra
le 30 Juin 2020
maybe your model is getting overfit.
try to adopt some dropout and regularization in your model.
0 commentaires
Nagasai Bharat
le 29 Sep 2020
Hi,
This issue may be mainly due to the overfitting of the data with respect to your model. As dropout is already applied while training you could use regularization methods (E.g. Batch Normalization, L2 Norm) to the model while training. Also, you could try altering the learning rate so that the model does not overfit.
You can refer to the following documentation and other similar training functions.
0 commentaires
Voir également
Catégories
En savoir plus sur Get Started with Statistics and Machine Learning Toolbox dans Help Center et File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!