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 10 Question 50 Discussion

You need to train a regression model based on a dataset containing 50,000 records that is stored in BigQuery. The data includes a total of 20 categorical and numerical features with a target variable that can include negative values. You need to minimize effort and training time while maximizing model performance. What approach should you take to train this regression model?
B) Use BQML XGBoost regression to train the model
A) Create a custom TensorFlow DNN model.
C) Use AutoML Tables to train the model without early stopping.
D) Use AutoML Tables to train the model with RMSLE as the optimization objective

Google Professional Machine Learning Engineer Exam - Topic 10 Question 50 Discussion

Actual exam question for Google's Professional Machine Learning Engineer exam
Question #: 50
Topic #: 10
[All Professional Machine Learning Engineer Questions]

You need to train a regression model based on a dataset containing 50,000 records that is stored in BigQuery. The data includes a total of 20 categorical and numerical features with a target variable that can include negative values. You need to minimize effort and training time while maximizing model performance. What approach should you take to train this regression model?

Show Suggested Answer Hide Answer
Suggested Answer: B

https://cloud.google.com/bigquery-ml/docs/introduction


by Yuki at Aug 04, 2022, 01:45 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
Anglea
10 months ago
Custom DNN sounds like overkill for this task.
upvoted 0 times
...
Gertude
10 months ago
Definitely leaning towards option B, it’s proven!
upvoted 0 times
...
Thora
10 months ago
Wait, can RMSLE really handle negative target values?
upvoted 0 times
...
Talia
11 months ago
I think AutoML Tables is the way to go here.
upvoted 0 times
...
Dorsey
11 months ago
BQML XGBoost is super efficient for large datasets!
upvoted 0 times
...
Wilda
11 months ago
Creating a custom TensorFlow model sounds complex for this task. I think leveraging AutoML might be more efficient given the dataset size.
upvoted 0 times
...
Gladys
11 months ago
I feel like using RMSLE could be beneficial since the target can have negative values, but I’m not confident about the specifics of that optimization.
upvoted 0 times
...
Laila
11 months ago
I’m not entirely sure, but I think AutoML could save time. I just can’t recall if early stopping is necessary for this scenario.
upvoted 0 times
...
Renea
11 months ago
I remember we discussed using BQML for regression tasks, especially with large datasets. XGBoost seems like a solid choice for performance.
upvoted 0 times
...
Kaitlyn
11 months ago
I'm pretty confident about this one. DCO seems to provide real-time visibility and better collaboration between business and IT, so I'll go with A and D.
upvoted 0 times
...
Kimberely
11 months ago
From what I remember, STDI2E is for imputing missing values, so that could be a viable solution. I'll have to double-check the details though.
upvoted 0 times
...

Save Cancel