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 88 discussion

Actual exam question from Microsoft's DP-100
Question #: 88
Topic #: 3
[All DP-100 Questions]

You create a binary classification model by using Azure Machine Learning Studio.
You must tune hyperparameters by performing a parameter sweep of the model. The parameter sweep must meet the following requirements:
✑ iterate all possible combinations of hyperparameters
✑ minimize computing resources required to perform the sweep
You need to perform a parameter sweep of the model.
Which parameter sweep mode should you use?

  • A. Random sweep
  • B. Sweep clustering
  • C. Entire grid
  • D. Random grid
Show Suggested Answer Hide Answer
Suggested Answer: C 🗳️
by jmonk at May 28, 2020, 9:53 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 4 years ago
Random grid: You can also reduce the size of the grid and run a random grid sweep. Research has shown that this method yields the same results, but is more efficient computationally. https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/tune-model-hyperparameters
upvoted 20 times
...
rr200
Highly Voted 3 years, 11 months ago
D is right. A is incorrect, as Random Sweep does not iterate all possible combination and randomly select parameters B is incorrect, as it is only for clustering algos C is incorrect, as Entire grid is resource intensive
upvoted 9 times
...
f82411e
Most Recent 3 weeks, 4 days ago
Selected Answer: C
C is Correct
upvoted 1 times
...
7bbe541
2 months ago
Selected Answer: C
should be C "iterate all possible combinations of hyperparameters"
upvoted 2 times
...
phdykd
11 months, 2 weeks ago
The question's requirements seem a bit contradictory as it asks to "iterate all possible combinations of hyperparameters" (which points to Entire Grid) but also to "minimize computing resources required to perform the sweep" (which points to Random Sweep/Grid). If we prioritize iterating over all combinations, then Entire Grid would be chosen. However, if we prioritize minimizing computational resources, then Random Sweep/Grid would be more suitable. As the question initially asks for iterating over all combinations, I chose Entire Grid in my previous response, but I acknowledge that if resource usage is a primary concern, Random Sweep/Grid would be more appropriate.
upvoted 5 times
PI_Team
11 months ago
I agree with you. To meet the requirement of iterating all possible combinations of hyperparameters while minimizing computing resources, you should use the “Entire grid” parameter sweep mode in Azure Machine Learning Studio. This mode performs a grid search over the entire hyperparameter space, trying all possible combinations of hyperparameter values. While this can be computationally expensive, it ensures that all combinations are tried and can result in finding the best combination of hyperparameters for your model. To minimize computing resources, you can carefully choose the range and granularity of the hyperparameters to be swept, and use parallel processing to speed up the sweep
upvoted 1 times
...
...
phdykd
1 year, 4 months ago
C. To iterate all possible combinations of hyperparameters, you should use the "Entire grid" parameter sweep mode in Azure Machine Learning Studio. This mode will sweep over all possible combinations of the hyperparameters that you specify. While the "Random sweep" and "Random grid" modes can also help you minimize computing resources by only evaluating a subset of possible combinations, they may not guarantee that you will evaluate all possible combinations of hyperparameters. On the other hand, the "Sweep clustering" mode is not a valid parameter sweep mode in Azure Machine Learning Studio.
upvoted 1 times
...
ning
2 years ago
I do not understand this question, there might be something messed up https://docs.microsoft.com/en-us/azure/machine-learning/component-reference/tune-model-hyperparameters Only two options are: entire grid and random sweep, also it is stated only entire grid can try all possible combinations of values, so in any sense it cannot be D
upvoted 4 times
ning
2 years ago
The question is asking for check all possible combinations, not asking for the best results ...
upvoted 1 times
...
...
pancman
2 years, 2 months ago
This question is outdated. In the newer version of ML Studio there are only two options to specify the parameter sweeping mode: 1) Entire grid 2) Random sweep
upvoted 1 times
...
Ankicaa
2 years, 3 months ago
This is confusing. In Azure ML Studio and in Documentation is clearly that only options are entire grid and random sweep. But does random sweep tries every possible combination?
upvoted 1 times
...
MohammadKhubeb
2 years, 4 months ago
Entire Grid is NOT because it is used when we do not know the best parameters to choose. Here, the binary classification is provided. So we need to select either Random Grid or Random Sweep.
upvoted 1 times
...
TheCyanideLancer
2 years, 5 months ago
given ans looks to be correct. Just try opening Tune Model Hyperparameters in old machine learning studio classic. The module has THREE options of Entire Grid, Random Sweep and Random Grid
upvoted 2 times
...
dija123
2 years, 6 months ago
Selected Answer: D
I vote for D
upvoted 1 times
...
mikosann
2 years, 8 months ago
Correct answer is Entire Grid. The document clearly states that Entire Grid should be used to try every possible combinations. https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/tune-model-hyperparameters
upvoted 3 times
...
claudiapatricia777
2 years, 8 months ago
The correct answer is A- Random Sweep, since in Azure Machine Learning Studio we only have 2 options - Random Sweep and Entire Grid: https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/tune-model-hyperparameters#bkmk_sweep
upvoted 1 times
...
prasad06
2 years, 9 months ago
Is this still being asked ? Applies to: Machine Learning Studio (classic) only
upvoted 1 times
...
trickerk
2 years, 11 months ago
If you still have some doubt, then please read https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/tune-model-hyperparameters: "You can also reduce the size of the grid and run a random grid sweep. Research has shown that this method yields the same results, but is more efficient computationally." So, given answer is correct!
upvoted 2 times
...
rishi_ram
3 years, 1 month ago
You can also reduce the size of the grid and run a random grid sweep. Research has shown that this method yields the same results, but is more efficient computationally. for those who are confused Ans is correct refer to link provided in Ans there you will get the below line : You can also reduce the size of the grid and run a random grid sweep. Research has shown that this method yields the same results, but is more efficient computationally.
upvoted 1 times
...
Load full discussion...
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