Microsoft DP-100 Exam - Topic 1 Question 66 Discussion

Actual exam question for Microsoft's DP-100 exam

Question #: 66
Topic #: 1

You use the Azure Machine Learning SDK to run a training experiment that trains a classification model and calculates its accuracy metric.

The model will be retrained each month as new data is available.

You must register the model for use in a batch inference pipeline.

You need to register the model and ensure that the models created by subsequent retraining experiments are registered only if their accuracy is higher than the currently registered model.

What are two possible ways to achieve this goal? Each correct answer presents a complete solution.

NOTE: Each correct selection is worth one point.

ASpecify a different name for the model each time you register it.

BRegister the model with the same name each time regardless of accuracy, and always use the latest

CSpecify the model framework version when registering the model, and only register subsequent models if this value is higher.

DSpecify a property named accuracy with the accuracy metric as a value when registering the model, and only register subsequent models if their accuracy is higher than the accuracy property value of the
currently registered model.

ESpecify a tag named accuracy with the accuracy metric as a value when registering the model, and only register subsequent models if their accuracy is higher than the accuracy tag value of the currently
registered model.

Show Suggested Answer

Suggested Answer: C, E

E: Using tags, you can track useful information such as the name and version of the machine learning library used to train the model. Note that tags must be alphanumeric.

https://notebooks.azure.com/xavierheriat/projects/azureml-getting-started/html/how-to-use-azureml/deployment/register-model-create-image-deploy-service/register-model-create-image-deploy-service.ipynb

by Lawrence at May 04, 2022, 05:28 PM

Limited Time Offer

25%

Off

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

Contribute your Thoughts:

Submit Cancel

Emeline

4 months ago

B is definitely not the way to go, always using the latest could cause issues.

upvoted 0 times

...

Kristeen

4 months ago

Wait, can you really register models with the same name? That seems risky.

upvoted 0 times

...

Colene

4 months ago

A is a bad idea, you’d end up with too many models to manage!

upvoted 0 times

...

Jin

5 months ago

I think E could work too, tagging is a good way to track metrics.

upvoted 0 times

...

Irene

5 months ago

Option D sounds right, using accuracy as a property makes sense.

upvoted 0 times

...

Lezlie

5 months ago

I’m a bit confused about option B. If we register the same model regardless of accuracy, how would we know if we have a better model? That doesn’t seem like a good strategy.

upvoted 0 times

...

Rebbecca

5 months ago

I practiced a similar question where we had to manage model versions, and I think option E could work if it uses tags for accuracy.

upvoted 0 times

...

Graciela

5 months ago

I'm not entirely sure, but I think specifying a different name each time, like in option A, could lead to a lot of clutter. That doesn't seem efficient.

upvoted 0 times

...

Elenora

5 months ago

I remember something about registering models with properties, so maybe option D sounds right since it mentions using the accuracy metric.

upvoted 0 times

...

Micheal

5 months ago

This looks like a good opportunity to apply my knowledge of operations management. I'll methodically go through each option and select the ones that best fit the supervisor's role.

upvoted 0 times

...

Gladys

5 months ago

Okay, I think I've got this. The XSLT style sheet is simply copying the content of the "city" element to the "data" element, so the output should be the text "Tokyo" enclosed in a "data" tag.

upvoted 0 times

...

Neghir

4 years ago

Answer are D and E : model version is not a value that evaluates predictions performance

upvoted 1 times

...