Deal of The Day! Hurry Up, Grab the Special Discount - Save 25% - Ends In 00:00:00 Coupon code: SAVE25
Welcome to Pass4Success

- Free Preparation Discussions
Mail Us support@pass4success.com
Location US
Mob_nav_barsMENU

Google Professional Machine Learning Engineer Exam - Topic 9 Question 10 Discussion

Your team trained and tested a DNN regression model with good results. Six months after deployment, the model is performing poorly due to a change in the distribution of the input data. How should you address the input differences in production?
C) Retrain the model, and select an L2 regularization parameter with a hyperparameter tuning service
A) Create alerts to monitor for skew, and retrain the model.
B) Perform feature selection on the model, and retrain the model with fewer features
D) Perform feature selection on the model, and retrain the model on a monthly basis with fewer features

Google Professional Machine Learning Engineer Exam - Topic 9 Question 10 Discussion

Actual exam question for Google's Professional Machine Learning Engineer exam
Question #: 10
Topic #: 9
[All Professional Machine Learning Engineer Questions]

Your team trained and tested a DNN regression model with good results. Six months after deployment, the model is performing poorly due to a change in the distribution of the input dat

a. How should you address the input differences in production?

Show Suggested Answer Hide Answer
Suggested Answer: C

by Myra at May 03, 2022, 11:26 AM

Limited Time Offer

25%

Off

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

Contribute your Thoughts:

0/2000 characters
Submit Cancel
Tanja
10 months ago
L2 regularization could help, but not sure if it’s the main issue here.
upvoted 0 times
...
Valentin
10 months ago
Wait, can a model really just stop working like that?
upvoted 0 times
...
Aracelis
11 months ago
Monthly retraining sounds excessive, but might be necessary.
upvoted 0 times
...
Barney
11 months ago
I think feature selection is overrated; just retrain with all features.
upvoted 0 times
...
Malika
11 months ago
Definitely need to monitor for skew and retrain the model.
upvoted 0 times
...
Melissa
11 months ago
I think option D could be useful since it combines feature selection and regular retraining, but I'm not confident about the frequency.
upvoted 0 times
...
Merilyn
11 months ago
I feel like we practiced a similar question where feature selection was mentioned, but I can't recall if it was the best approach here.
upvoted 0 times
...
Deonna
11 months ago
I remember we discussed the importance of monitoring for data drift, so option A seems like a good choice.
upvoted 0 times
...
Wilson
11 months ago
I'm not entirely sure, but I think retraining the model regularly could help. Maybe option C is worth considering?
upvoted 0 times
...
Nenita
11 months ago
This looks like a straightforward integration design using Azure Functions and Service Bus. I think I can handle this.
upvoted 0 times
...
Cherri
11 months ago
Okay, I've got this. SAML is the XML-based standard for identity and access management, used to securely exchange authentication and authorization data. I'm feeling good about selecting that as the answer.
upvoted 0 times
...
Jacquline
11 months ago
Hmm, this looks like a tricky one. I'll need to carefully read through the question and the provided code to make sure I understand the requirements before attempting to solve it.
upvoted 0 times
...
Lauryn
11 months ago
Okay, let me focus on the key details here. I think I can figure this out.
upvoted 0 times
...

Save Cancel