Google Professional Machine Learning Engineer Exam - Topic 9 Question 46 Discussion

Actual exam question for Google's Professional Machine Learning Engineer exam

Question #: 46
Topic #: 9

[All Professional Machine Learning Engineer Questions]

You need to build classification workflows over several structured datasets currently stored in BigQuery. Because you will be performing the classification several times, you want to complete the following steps without writing code: exploratory data analysis, feature selection, model building, training, and hyperparameter tuning and serving. What should you do?

AConfigure AutoML Tables to perform the classification task

BRun a BigQuery ML task to perform logistic regression for the classification

CUse Al Platform Notebooks to run the classification model with pandas library

DUse Al Platform to run the classification model job configured for hyperparameter tuning

Show Suggested Answer

Suggested Answer: B

BigQuery ML supports supervised learning with thelogistic regressionmodel type.

by Cammy at May 30, 2022, 01:00 PM

Limited Time Offer

25%

Off

Get Premium Professional Machine Learning Engineer Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

Submit Cancel

Lilli

4 months ago

Not sure if AutoML is the best for hyperparameter tuning though.

upvoted 0 times

...

Richelle

4 months ago

Totally agree, AutoML makes it easy!

upvoted 0 times

...

Celia

4 months ago

Wait, can AutoML really handle all those steps without any coding?

upvoted 0 times

...

Nikita

4 months ago

I think BigQuery ML is more straightforward for this.

upvoted 0 times

...

Florinda

4 months ago

AutoML Tables is a great choice for no-code workflows!

upvoted 0 times

...

Wade

5 months ago

Hyperparameter tuning sounds important, but I can't recall if AI Platform is the best way to handle everything without coding.

upvoted 0 times

...

Elbert

5 months ago

I practiced with AI Platform Notebooks before, but I feel like that involves more coding than what the question is asking for.

upvoted 0 times

...

Mose

5 months ago

I'm not entirely sure, but I think BigQuery ML might be a good option too, especially for logistic regression.

upvoted 0 times

...

Tamar

5 months ago

I remember studying AutoML Tables, and it seems like the right choice since it automates many steps in the classification process.

upvoted 0 times

...

Ronny

5 months ago

I'd go with containers. They're lightweight, portable, and can be easily managed across multiple clouds. Seems like the perfect fit for this company's needs.

upvoted 0 times

...

Marguerita

5 months ago

Placing the customer on hold to allow them to calm down seems like the most logical choice here. You want to give them a chance to cool off before trying to resolve the issue.

upvoted 0 times

...

Anastacia

5 months ago

I'm leaning towards 7.0 percent because I remember a similar question where they used a constant dividend approach.

upvoted 0 times

...

Alex

5 months ago

I'm a little confused by the question. It seems like we need to route traffic based on the visitor's location, but I'm not sure if Geolocation is the only option. Maybe the Multivalue answer routing policy could work too, since it allows you to return multiple IP addresses and let the client choose the best one.

upvoted 0 times

...