Give some suggestions to avoid overfitting

I'm training a neural networks which basicly does binary classification, but it overfits too fast. After 4-5 epochs it's already in overfitting. What is the reason of it? How to avoid from fast overfitting?

neural-networksoverfit
1 votesNN132.00
1 Answers
JO218.00
1

There are couple of basic steps to do for avoiding overfitting

  1. Make the model smaller
  2. Increase examples in your dataset
  3. Add regularizations
  4. Try K-fold validation
  5. If you use transfer learning, try to freeze certain part of it
Reply
Couldn't find what you were looking for?and we will find an expert to answer.
How helpful was this page?