Google Professional Machine Learning Engineer Exam - Topic 2 Question 95 Discussion

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

Question #: 95
Topic #: 2

[All Professional Machine Learning Engineer Questions]

You are an ML engineer at a manufacturing company. You need to build a model that identifies defects in products based on images of the product taken at the end of the assembly line. You want your model to preprocess the images with lower computation to quickly extract features of defects in products. Which approach should you use to build the model?

AReinforcement learning

BRecommender system

CRecurrent Neural Networks (RNN)

DConvolutional Neural Networks (CNN)

Show Suggested Answer

Suggested Answer: D

by Dell at Jan 13, 2025, 09:25 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

Selene

3 months ago

Just a reminder, CNNs are designed for spatial data like images.

upvoted 0 times

...

Latricia

3 months ago

Wait, why not use reinforcement learning? Seems interesting.

upvoted 0 times

...

Matthew

4 months ago

CNNs are the best choice for this type of task!

upvoted 0 times

...

Kate

4 months ago

RNNs are not the right fit here, right?

upvoted 0 times

...

Kimbery

4 months ago

Definitely going with CNN for image processing!

upvoted 0 times

...

Desiree

4 months ago

Reinforcement learning seems off for this task since it's more about decision-making rather than image analysis. I lean towards CNNs too.

upvoted 0 times

...

Johnetta

4 months ago

I practiced a similar question about image classification, and I think CNNs were highlighted as the go-to method for feature extraction in images.

upvoted 0 times

...

Aleisha

5 months ago

I'm not entirely sure, but I feel like RNNs are more for sequential data, not images. So maybe that's not the best option?

upvoted 0 times

...

Odette

5 months ago

I remember studying that CNNs are specifically designed for image processing, so I think option D might be the right choice.

upvoted 0 times

...

Janae

5 months ago

Hmm, I'm not sure if Recurrent Neural Networks (RNN) are the best fit for this problem. They're usually better suited for sequential data, like text or time series. I think I'll go with Convolutional Neural Networks (CNN).

upvoted 0 times

...

Eleni

5 months ago

Convolutional Neural Networks (CNN) are definitely the way to go here. They're designed to handle image data and can extract relevant features with relatively low computational cost.

upvoted 0 times

...

Bernardine

5 months ago

I'm a bit unsure about this one. Reinforcement learning could work, but it might be overkill for a simple defect detection task. I'll have to think this through more carefully.

upvoted 0 times

...

Timothy

5 months ago

This seems like a classic computer vision problem, so I'd go with Convolutional Neural Networks (CNN). They're great at extracting features from images efficiently.

upvoted 0 times

...

Lisha

9 months ago

CNN is the way to go, but I'm also curious if they have any defective products that could be used as training data. You know, for a little 'quality control' practice.

upvoted 0 times

...

Ty

9 months ago

I heard CNN stands for 'Cats, Catnip, and Napping'. I'm pretty sure that's not what we're looking for in this case.

upvoted 0 times

...

Sean

10 months ago

Reinforcement learning? That's for training agents to take actions in an environment. I think you need to go back and review your machine learning fundamentals, my friend.

upvoted 0 times

...

Edison

10 months ago

Recommender systems? Really? I think you might be confusing this with a completely different problem. CNN is the clear choice here.

upvoted 0 times

Dacia

8 months ago

RNN might not be the most efficient choice for image feature extraction.

upvoted 0 times

...

Vivan

9 months ago

Recommender systems are not suitable for this problem.

upvoted 0 times

...

Justine

9 months ago

CNN is definitely the way to go for image processing.

upvoted 0 times

...

Lavonne

9 months ago

I think CNN is the best approach for this task.

upvoted 0 times

...

Rebecka

10 months ago

I was thinking RNN might work, but CNN is probably a better fit since we're dealing with images rather than sequential data.

upvoted 0 times

Ilene

10 months ago

Let's go with CNN for our model to identify defects in products based on images.

upvoted 0 times

...

Fallon

10 months ago

RNNs might work for sequential data, but CNNs are more suitable for image analysis.

upvoted 0 times

...

Pauline

10 months ago

CNNs are great at extracting features from images efficiently.

upvoted 0 times

...

Aide

10 months ago

I agree, CNN is definitely the way to go for image processing.

upvoted 0 times

...

Vashti

11 months ago

CNN is definitely the way to go here. It's designed to efficiently process and extract features from images, which is exactly what this problem requires.

upvoted 0 times