Google Professional Machine Learning Engineer Exam - Topic 6 Question 83 Discussion

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

Question #: 83
Topic #: 6

[All Professional Machine Learning Engineer Questions]

You developed a Vertex Al pipeline that trains a classification model on data stored in a large BigQuery table. The pipeline has four steps, where each step is created by a Python function that uses the KubeFlow v2 API The components have the following names:

You launch your Vertex Al pipeline as the following:

You perform many model iterations by adjusting the code and parameters of the training step. You observe high costs associated with the development, particularly the data export and preprocessing steps. You need to reduce model development costs. What should you do?

AOption A

BOption B

COption C

DOption D

Show Suggested Answer

Suggested Answer: C

by Marci at Jul 15, 2024, 10:42 AM

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

Ellen

4 months ago

Not sure if any option will really cut costs significantly.

upvoted 0 times

...

An

4 months ago

Totally agree with Option A, it targets the right steps.

upvoted 0 times

...

Shanda

4 months ago

Wait, are we really considering data export costs? That's surprising!

upvoted 0 times

...

Bulah

5 months ago

I disagree, I think Option C might be better.

upvoted 0 times

...

Eun

5 months ago

Option A seems like a solid choice for cost reduction.

upvoted 0 times

...

Harrison

5 months ago

I vaguely remember something about using BigQuery more efficiently, maybe by leveraging its built-in functions instead of exporting data.

upvoted 0 times

...

Staci

5 months ago

I feel like we should focus on the preprocessing step since that's where the high costs are, but I’m uncertain about the best approach.

upvoted 0 times

...

Cammy

5 months ago

I think one of the practice questions mentioned using batch processing to reduce costs, but I can't recall the specifics.

upvoted 0 times

...

Trina

5 months ago

I remember we discussed optimizing data export costs, but I'm not sure which option directly addresses that.

upvoted 0 times

...

Margurite

5 months ago

This is a great question that really tests our understanding of Vertex AI pipelines and cost optimization. I feel confident that I can analyze the situation and propose an effective solution to reduce the development costs.

upvoted 0 times

...

Stephaine

5 months ago

Hmm, I'm a bit confused by the different pipeline steps and how they relate to the costs. I'll need to review the details more closely to understand what's going on and come up with a good solution.

upvoted 0 times

...

Kaitlyn

5 months ago

This looks like a tricky question, but I think I can tackle it. I'll need to carefully analyze the pipeline steps and the cost breakdown to determine the best approach to reduce the development costs.

upvoted 0 times

...

Julio

6 months ago

Okay, I've got a strategy in mind. I think the key is to focus on optimizing the data export and preprocessing steps, since those seem to be the main cost drivers. I'll need to dig into the code and see if there are any opportunities to streamline those processes.

upvoted 0 times

...

Mel

6 months ago

This question is a bit confusing, but I'll try to break it down. I'm pretty sure the business partner and contract account are the two correct answers here.

upvoted 0 times

...

Jose

6 months ago

I'm feeling pretty confident about this one. Real Agents, Profile Agents, Scenario period, and Shifts are definitely the right answers. I'll mark those and submit my response.

upvoted 0 times

...

Bernardine

11 months ago

Wait, is this a trick question? What if the answer is actually 'All of the above' and we have to choose the most 'cost-effective' one? Guess I'll go with C just to be safe.

upvoted 0 times