Microsoft DP-100 Exam - Topic 7 Question 63 Discussion

Actual exam question for Microsoft's DP-100 exam

Question #: 63
Topic #: 7

You create a script that trains a convolutional neural network model over multiple epochs and logs the validation loss after each epoch. The script includes arguments for batch size and learning rate.

You identify a set of batch size and learning rate values that you want to try.

You need to use Azure Machine Learning to find the combination of batch size and learning rate that results in the model with the lowest validation loss.

What should you do?

ARun the script in an experiment based on an AutoMLConfig object

BCreate a PythonScriptStep object for the script and run it in a pipeline

CUse the Automated Machine Learning interface in Azure Machine Learning studio

DRun the script in an experiment based on a ScriptRunConfig object

ERun the script in an experiment based on a HyperDriveConfig object

Show Suggested Answer

Suggested Answer: E

https://docs.microsoft.com/en-us/azure/machine-learning/how-to-tune-hyperparameters

by Nelida at May 03, 2022, 05:19 PM

Limited Time Offer

25%

Off

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

Contribute your Thoughts:

Submit Cancel

Carmelina

4 months ago

I disagree, I’d stick with the pipeline approach instead.

upvoted 0 times

...

Margot

5 months ago

Wait, can HyperDrive really find the best combo that fast?

upvoted 0 times

...

Susy

5 months ago

Definitely leaning towards option E!

upvoted 0 times

...

Keneth

5 months ago

I think AutoMLConfig could work too, but not as flexible.

upvoted 0 times

...

Emmanuel

5 months ago

HyperDriveConfig is the way to go for tuning hyperparameters!

upvoted 0 times

...

Farrah

5 months ago

I’m confused about whether to use HyperDriveConfig or ScriptRunConfig. I feel like both could potentially help, but I need to recall the differences better.

upvoted 0 times

...

Amina

5 months ago

I’m leaning towards the HyperDriveConfig option too, but I wonder if using a pipeline with PythonScriptStep could work as well.

upvoted 0 times

...

Leandro

5 months ago

I remember practicing with AutoMLConfig, but I feel like that’s more for automated model selection rather than tuning specific parameters like batch size and learning rate.

upvoted 0 times

...

Man

5 months ago

I think we might need to use HyperDriveConfig since it’s specifically for hyperparameter tuning, right? But I'm not entirely sure.

upvoted 0 times

...

Britt

5 months ago

Hmm, this is a tricky one. I'm not entirely sure about the best approach here. I'll need to think through each option and consider what's true and what's not.

upvoted 0 times

...

Geoffrey

6 months ago

Okay, let's think this through step-by-step. We know that 1 liter of the solution contains 5 grams of the drug. So we need to figure out how much is in 750 ml, which is 3/4 of a liter.

upvoted 0 times

...