Microsoft Exam DP-100 Topic 4 Question 121 Discussion

Actual exam question for Microsoft's DP-100 exam

Question #: 121
Topic #: 4

You use Azure Machine Learning to train a model.

You must use a sampling method for tuning hyperparameters. The sampling method must pick samples based on how the model performed with previous samples.

You need to select a sampling method.

Which sampling method should you use?

AGrid

BBayesian

CRandom

Show Suggested Answer

Suggested Answer: B

by Clay at Jan 26, 2025, 07:10 AM

Limited Time Offer

25%

Off

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

Contribute your Thoughts:

Submit Cancel

Vince

3 months ago

If I choose random sampling, I might as well just throw darts at the answer choices and hope for the best. Bayesian is the way to go, hands down.

upvoted 0 times

Margurite

2 months ago

B) Bayesian

upvoted 0 times

...

Giuseppe

2 months ago

A) Grid

upvoted 0 times

...

Dorian

3 months ago

Bayesian sampling is the clear winner here. It's like having a crystal ball that tells you which samples to try next. Grid and random sampling are so last century.

upvoted 0 times

Rodrigo

2 months ago

User 3: Grid and random sampling are outdated compared to Bayesian sampling.

upvoted 0 times

...

Kenny

2 months ago

User 2: I agree, Bayesian sampling is like having a crystal ball for picking the right samples.

upvoted 0 times

...

Isidra

2 months ago

User 1: I think we should use Bayesian sampling for tuning hyperparameters.

upvoted 0 times

...

Jonelle

3 months ago

Grid sampling might work, but it's not the most efficient method for tuning hyperparameters. Bayesian is the way to go if you want to optimize your model's performance.

upvoted 0 times

Barbra

2 months ago

Random sampling might not be as effective as Bayesian for this task.

upvoted 0 times

...

Lon

2 months ago

I agree, Bayesian sampling is more efficient for tuning hyperparameters.

upvoted 0 times

...

Anastacia

3 months ago

I think Bayesian sampling would be the best choice.

upvoted 0 times

...

Arlette

4 months ago

I'm not sure. Grid sampling is also a valid option, as it exhaustively searches through all possible combinations.

upvoted 0 times

...

Myong

4 months ago

Random sampling? Really? That doesn't sound like it would be very effective for tuning hyperparameters. I'm going with Bayesian on this one.

upvoted 0 times

Boris

3 months ago

Random sampling might not be the most effective method for this task.

upvoted 0 times

...

Filiberto

3 months ago

I agree, Bayesian sampling is a better choice for tuning hyperparameters.

upvoted 0 times

...

Sanjuana

4 months ago

I agree with Gracie. Bayesian sampling considers previous samples, which can lead to better hyperparameter tuning.

upvoted 0 times

...

Gracie

4 months ago

I think we should use Bayesian sampling.

upvoted 0 times

...

Merissa

4 months ago

I think Bayesian sampling would be the best choice here. It's designed to pick samples based on previous performance, which is exactly what the question asks for.

upvoted 0 times