Deal of The Day! Hurry Up, Grab the Special Discount - Save 25% - Ends In 00:00:00 Coupon code: SAVE25
Welcome to Pass4Success

- Free Preparation Discussions

Microsoft DP-100 Exam - Topic 2 Question 80 Discussion

Actual exam question for Microsoft's DP-100 exam
Question #: 80
Topic #: 2
[All DP-100 Questions]

You have an Azure Machine Learning workspace. You plan to tune model hyperparameters by using a sweep job.

You need to find a sampling method that supports early termination of low-performance jobs and continuous hyperpara meters.

Solution: Use the Sobol sampling method over the hyperpara meter space.

Does the solution meet the goal?

Show Suggested Answer Hide Answer
Suggested Answer: C

import azureml.contrib.fairness package to perform the upload:

from azureml.contrib.fairness import upload_dashboard_dictionary, download_dashboard_by_upload_id


https://docs.microsoft.com/en-us/azure/machine-learning/how-to-machine-learning-fairness-aml

Contribute your Thoughts:

0/2000 characters
Cathrine
5 months ago
Definitely not the best method for that purpose.
upvoted 0 times
...
Dorinda
5 months ago
Wait, can Sobol really do early stopping? That's new to me!
upvoted 0 times
...
Mauricio
5 months ago
I agree, it seems like a solid choice for hyperparameter tuning.
upvoted 0 times
...
Paris
5 months ago
I thought Sobol doesn't support early termination though?
upvoted 0 times
...
Ashley
5 months ago
Sobol sampling is great for continuous parameters!
upvoted 0 times
...
Tabetha
6 months ago
I could be wrong, but I thought Sobol was mainly for discrete parameters. I need to double-check if it works with continuous ones too.
upvoted 0 times
...
Melvin
6 months ago
I feel like Sobol is more about uniform sampling rather than focusing on performance, so I might lean towards "No" for this one.
upvoted 0 times
...
Brice
6 months ago
I remember practicing a question about sampling methods, and I think the Bayesian optimization method was mentioned for early termination.
upvoted 0 times
...
Reta
6 months ago
I think the Sobol method is good for exploring the hyperparameter space, but I'm not sure if it supports early termination.
upvoted 0 times
...
Marleen
6 months ago
I feel pretty confident that the answer is D. The question doesn't seem to be limiting the suitability of modular data center products to any specific size, so all of the options must be correct.
upvoted 0 times
...
Shelia
6 months ago
Hmm, I'm not totally sure about this one. I'll have to think it through carefully.
upvoted 0 times
...
Gary
6 months ago
Hmm, breaking a mirror and moving data to a new mount point - that's a common admin task, but the details here seem a bit complex. I'll need to think through each step carefully.
upvoted 0 times
...
Nikita
6 months ago
I think it might be related to DNS, like ensuring the DNS entry points to the virtual IP. It was mentioned in some practice questions.
upvoted 0 times
...
Vanna
11 months ago
Sobol sampling? More like Sobo-rific! I bet the developer who came up with that name was feeling pretty clever. But hey, if it gets the job done, I'm all for it.
upvoted 0 times
Louvenia
10 months ago
B) No
upvoted 0 times
...
Elbert
10 months ago
I agree, Sobol sampling sounds interesting. Let's give it a try.
upvoted 0 times
...
Nickole
10 months ago
B) No
upvoted 0 times
...
Madonna
10 months ago
I agree, Sobol sampling sounds interesting. Let's give it a try.
upvoted 0 times
...
Rueben
10 months ago
A) Yes
upvoted 0 times
...
Luisa
10 months ago
A) Yes
upvoted 0 times
...
...
Lawanda
11 months ago
The solution sounds good to me! Now, if only I could figure out how to make the Azure ML workspace do my laundry too...
upvoted 0 times
Tammi
9 months ago
User 3: A) Yes
upvoted 0 times
...
Charolette
9 months ago
User 2: B) No
upvoted 0 times
...
Clorinda
9 months ago
User 1: A) Yes
upvoted 0 times
...
Dalene
10 months ago
The solution sounds good to me! Now, if only I could figure out how to make the Azure ML workspace do my laundry too...
upvoted 0 times
...
Noah
11 months ago
B) No
upvoted 0 times
...
Nickole
11 months ago
A) Yes
upvoted 0 times
...
...
Malcom
11 months ago
Ah, the age-old question of hyperparameter tuning. Sobol sampling, huh? Sounds like it could work, but I'd love to see some real-world examples before committing to it.
upvoted 0 times
...
Elli
11 months ago
Hmm, I'm not sure. Sobol sampling sounds fancy, but I wonder if it's really the best fit for this use case. Maybe I should do some more research.
upvoted 0 times
...
Martina
11 months ago
Sobol sampling is great for early termination and continuous hyperparameters. This solution definitely meets the goal!
upvoted 0 times
...
Elenore
12 months ago
But Sobol sampling method is known for its efficiency in exploring hyperparameter space.
upvoted 0 times
...
Hollis
12 months ago
I disagree, I don't think Sobol sampling method supports early termination.
upvoted 0 times
...
Elenore
12 months ago
I think the solution meets the goal.
upvoted 0 times
...

Save Cancel