ExamTopics Logo
Mail Us[email protected]
Menu
Microsoft Discussions
exam questions

Exam DP-100 All Questions

View all questions & answers for the DP-100 exam
Go to Exam

Exam DP-100 topic 3 question 89 discussion

Actual exam question from Microsoft's DP-100
Question #: 89
Topic #: 3
[All DP-100 Questions]

You are building a recurrent neural network to perform a binary classification.
You review the training loss, validation loss, training accuracy, and validation accuracy for each training epoch.
You need to analyze model performance.
You need to identify whether the classification model is overfitted.
Which of the following is correct?

  • A. The training loss stays constant and the validation loss stays on a constant value and close to the training loss value when training the model.
  • B. The training loss decreases while the validation loss increases when training the model.
  • C. The training loss stays constant and the validation loss decreases when training the model.
  • D. The training loss increases while the validation loss decreases when training the model.
Show Suggested Answer Hide Answer
Suggested Answer: B 🗳️
by ajithvajrala at May 23, 2020, 11:20 a.m.

Comments

Chosen Answer:
This is a voting comment (?). It is better to Upvote an existing comment if you don't have anything to add.
Switch to a voting comment New
Submit Cancel
pepmir
Highly Voted 3 years, 12 months ago
Def of Overfit: Train Accuracy is High (aka Less Loss), Test Accuracy is Low (aka High Loss) Going by this, answer B is correct to me
upvoted 30 times
...
Shankar_102
Highly Voted 3 years, 4 months ago
This answer is correct guys
upvoted 7 times
...
evangelist
Most Recent 2 weeks ago
Selected Answer: B
B is correct
upvoted 1 times
...
Yuriy_Ch
1 year, 3 months ago
Selected Answer: B
Yes, B is correct
upvoted 1 times
...
michaelmorar
1 year, 5 months ago
Selected Answer: B
Increase in validation loss while training loss goes down to me is a good sign of overfitting.
upvoted 1 times
...
ljljljlj
2 years, 11 months ago
On exam 2021/7/10
upvoted 6 times
...
ajithvajrala
4 years, 1 month ago
The mentioned answer is wrong. The correct answer is graph-1--> negatively skewed Graph-2-> positively skewed reference: https://www.statisticshowto.com/probability-and-statistics/skewed-distribution/
upvoted 1 times
smilingsun247
3 years, 1 month ago
Right answer, Wrong question.
upvoted 8 times
...
damirbek369
3 years, 6 months ago
I believe, it is the answer to the next question, right?
upvoted 4 times
...
...
Community vote distribution
A (35%)
C (25%)
B (20%)
Other
Most Voted
A voting comment increases the vote count for the chosen answer by one.

Upvoting a comment with a selected answer will also increase the vote count towards that answer by one. So if you see a comment that you already agree with, you can upvote it instead of posting a new comment.

SaveCancel
exam
Someone Bought Contributor Access for:
SY0-701
London, 1 minute ago