New Year Sale 2026! Hurry Up, Grab the Special Discount - Save 25% - Ends In 00:00:00 Coupon code: SAVE25
Welcome to Pass4Success

- Free Preparation Discussions
Mail Us support@pass4success.com
Location US
Mob_nav_barsMENU

Microsoft DP-100 Exam - Topic 6 Question 42 Discussion

Actual exam question for Microsoft's DP-100 exam
Question #: 42
Topic #: 6
[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.

Which observation indicates that the classification model is over fitted?

Show Suggested Answer Hide Answer
Suggested Answer: B

by Merissa at May 05, 2022, 09:26 AM

Limited Time Offer

25%

Off

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

Contribute your Thoughts:

0/2000 characters
Submit Cancel
Patria
4 months ago
B is confusing, I thought it meant the model was improving.
upvoted 0 times
...
Cletus
4 months ago
A doesn't indicate overfitting, just saying.
upvoted 0 times
...
Erin
4 months ago
Wait, are we sure about C? Seems a bit off.
upvoted 0 times
...
Mel
5 months ago
Totally agree, C is the right choice!
upvoted 0 times
...
Marisha
5 months ago
C is the classic sign of overfitting.
upvoted 0 times
...
Cecilia
5 months ago
I practiced a similar question, and I recall that overfitting usually shows a divergence between training and validation losses. So, I guess option C makes sense.
upvoted 0 times
...
Denae
5 months ago
I'm not entirely sure, but I feel like if both losses are constant, it might indicate that the model isn't learning at all. Could that be option A?
upvoted 0 times
...
Aliza
5 months ago
I think I remember that if the training loss decreases but the validation loss starts to increase, that's a sign of overfitting. So maybe option C?
upvoted 0 times
...
Victor
5 months ago
I’m a bit confused, but I think if the training loss stays constant while the validation loss decreases, that might not indicate overfitting. Maybe option D is the right choice?
upvoted 0 times
...
Carma
5 months ago
I'm not sure about this one. The question seems a bit vague, and I'm not sure what a "batch fob" is. I'll have to think this through carefully.
upvoted 0 times
...
Elvis
5 months ago
Hmm, I'm a bit confused. The question mentions that only PaaS solutions can be used, but option C includes Azure virtual machines, which are IaaS. I'll need to double-check the differences between PaaS and IaaS to make sure I understand this properly.
upvoted 0 times
...
Stephen
5 months ago
I'm leaning towards Indexing as the correct answer. That's where the data is actually indexed and prepared for searching, which would include processing any extraction configurations.
upvoted 0 times
...
Kristeen
5 months ago
Fluid Experiences sounds familiar too, but I can't remember if it's meant for single-page apps or something else!
upvoted 0 times
...
Essie
5 months ago
I'm a bit unsure, but could the second blank be "Dynamic Data Normalization?" I saw a similar question where pointers were involved.
upvoted 0 times
...

Save Cancel