What to do when training doesn't fit training data well?

조회 수: 3(최근 30일)
Jordan Pauls
Jordan Pauls 2020년 5월 28일
답변: Nagasai Bharat 2020년 9월 29일
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.
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:
And cross validation prediction is even worse:
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!
  댓글 수: 3
vaibhav mishra
vaibhav mishra 2020년 6월 30일
maybe your model is getting overfit.
try to adopt some dropout and regularization in your model.

댓글을 달려면 로그인하십시오.

답변(2개)

vaibhav mishra
vaibhav mishra 2020년 6월 30일
maybe your model is getting overfit.
try to adopt some dropout and regularization in your model.

Nagasai Bharat
Nagasai Bharat 2020년 9월 29일
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.

제품


릴리스

R2020a

Community Treasure Hunt

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

Start Hunting!

Translated by