You also evaluate your model on the test set, and find the following:
Human-level performance 0.1% Training set error 2.0% Dev set error 2.1% Test set error 7.0% What does this mean? (Check the two best options.)
You have underfit to the dev set.
You should get a bigger test set.
You should try to get a bigger dev set.
You have overfit to the dev set.
Topic training machine-learning
Category Data Science
I think the answer should be 2.) and 4.). Since your training/dev set is performing well but the test set is not as good. Hence your model is overfitting to the training/dev set.
Also increasing the sample size of test set will help in bringing down this error.
I think answer are options 3) and 4)
Clearly there seems to be overfiting towards dev set as the dev set error is low and almost equal to training set error.
And increasing the number of samples helps minimizing overfiting problem..
Geeks Mental is a community that publishes articles and tutorials about Web, Android, Data Science, new techniques and Linux security.