Google Professional Machine Learning Engineer Exam - Topic 8 Question 40 Discussion

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

Question #: 40
Topic #: 8

[All Professional Machine Learning Engineer Questions]

You work for an online retail company that is creating a visual search engine. You have set up an end-to-end ML pipeline on Google Cloud to classify whether an image contains your company's product. Expecting the release of new products in the near future, you configured a retraining functionality in the pipeline so that new data can be fed into your ML models. You also want to use Al Platform's continuous evaluation service to ensure that the models have high accuracy on your test data set. What should you do?

AKeep the original test dataset unchanged even if newer products are incorporated into retraining

BExtend your test dataset with images of the newer products when they are introduced to retraining

CReplace your test dataset with images of the newer products when they are introduced to retraining.

DUpdate your test dataset with images of the newer products when your evaluation metrics drop below a pre-decided threshold.

Show Suggested Answer

Suggested Answer: C

by Kristofer at May 07, 2022, 02:37 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

Almeta

4 months ago

Isn't it better to just keep adding new images? B makes sense!

upvoted 0 times

...

Mammie

4 months ago

D could lead to delayed updates, not a fan of that approach.

upvoted 0 times

...

Refugia

4 months ago

Wait, why would you replace the whole dataset? C sounds risky.

upvoted 0 times

...

Emilio

4 months ago

I disagree, A is safer for consistency.

upvoted 0 times

...

Louisa

5 months ago

B seems like the best option to keep things relevant!

upvoted 0 times

...

Taryn

5 months ago

Keeping the original test dataset unchanged seems risky, especially with new products coming in. I would lean towards extending it.

upvoted 0 times

...

Tom

5 months ago

I feel like we practiced a question similar to this, and I think updating the test dataset when metrics drop sounds like a good strategy.

upvoted 0 times

...

Freeman

5 months ago

I'm not entirely sure, but I think replacing the test dataset could lead to issues with model evaluation.

upvoted 0 times

...

Mi

5 months ago

I remember we discussed the importance of keeping the test dataset relevant, so I think extending it with new product images makes sense.

upvoted 0 times

...

Tu

5 months ago

The way I see it, the Scrum Master shouldn't just let the Product Owner continue tracking progress at the Daily Scrum. That goes against the purpose of the event.

upvoted 0 times

...

Tomas

5 months ago

I'm a bit unsure on this one. Is it talking about a specific legal term, or just a general contract concept? I'll have to review my notes to see if I can narrow it down.

upvoted 0 times

...

Donette

5 months ago

I've got a good strategy - I'll focus on the options that seem most aligned with best practices for interface design, like minimizing parameters and making it hard to misuse.

upvoted 0 times

...

Jerilyn

5 months ago

I think this question is similar to one we practiced about service types, but I can't recall if it was entity or utility service that was correct.

upvoted 0 times

...