Microsoft Exam DP-100 Topic 9 Question 100 Discussion

Actual exam question for Microsoft's DP-100 exam

Question #: 100
Topic #: 9

You are building recurrent neural network to perform a binary classification.

The training loss, validation loss, training accuracy, and validation accuracy of each training epoch has been provided. You need to identify whether the classification model is over fitted.

Which of the following is correct?

AThe training loss increases while the validation loss decreases when training the model.

BThe training loss decreases while the validation loss increases when training the model.

CThe training loss stays constant and the validation loss decreases when training the model.

DThe training loss .stays constant and the validation loss stays on a constant value and close to the training loss value when training the model.

Show Suggested Answer

Suggested Answer: B

by Galen at Apr 19, 2024, 06:26 PM

Limited Time Offer

25%

Off

Get Premium DP-100 Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

Submit Cancel

Latanya

4 days ago

I'm a bit confused by this question. The options don't seem to match up with the typical signs of overfitting that I've learned about. I'll need to review my notes on model evaluation and generalization to make sure I understand this properly.

upvoted 0 times

...

Trina

8 days ago

Okay, let me break this down step-by-step. I want to make sure I understand the concept before answering.

upvoted 0 times

...

Quiana

18 days ago

Okay, I think I've got it. The key is to set the override date field to be more restrictive, either at the legal entity level (A) or the shared level (B). I'll double-check my work, but I'm feeling confident about this one.

upvoted 0 times

...

Frank

6 months ago

Option B is the answer, no doubt about it. It's just like my grandma used to say, 'If the training loss is down and the validation's up, your model's in a rut!'

upvoted 0 times

Ollie

4 months ago

We should consider techniques like early stopping or regularization to address overfitting.

upvoted 0 times

...

Terina

4 months ago

Exactly, it's important to monitor the training and validation loss to prevent overfitting.

upvoted 0 times

...

Gregg

5 months ago

I agree, that indicates the model is overfitting.

upvoted 0 times

...

Nan

5 months ago

I think option B is correct. The training loss decreases while the validation loss increases.

upvoted 0 times

...

Antonio

5 months ago

'If the training loss is down and the validation's up, your model's in a rut!'

upvoted 0 times

...

Luisa

5 months ago

Option B is the answer, no doubt about it.

upvoted 0 times

...

Ethan

6 months ago

Hmm, this is a tricky one. I'm going to have to think about it more. Maybe I should ask the professor to give me a hint - I heard they're quite fond of dad jokes.

upvoted 0 times

...