ExamTopics Logo
Mail Us[email protected]
Menu
Microsoft Discussions
exam questions

Exam AI-900 All Questions

View all questions & answers for the AI-900 exam
Go to Exam

Exam AI-900 topic 1 question 45 discussion

Actual exam question from Microsoft's AI-900
Question #: 45
Topic #: 1
[All AI-900 Questions]

When training a model, why should you randomly split the rows into separate subsets?

  • A. to train the model twice to attain better accuracy
  • B. to train multiple models simultaneously to attain better performance
  • C. to test the model by using data that was not used to train the model
Show Suggested Answer Hide Answer
Suggested Answer: C 🗳️
by ipindado2020 at Dec. 3, 2020, 7:40 p.m.

Comments

Chosen Answer:
This is a voting comment (?). It is better to Upvote an existing comment if you don't have anything to add.
Switch to a voting comment New
Submit Cancel
jurimec
Highly Voted 3 years, 11 months ago
this is the famous 70% & 30%?
upvoted 23 times
Nikhil007
3 years, 6 months ago
can you explain this a bit more?
upvoted 2 times
brollyy
3 years, 3 months ago
He is referring to the famous train_test_split that everyone uses to split the dataset into train and test sets.
upvoted 8 times
...
...
Massy
3 years, 11 months ago
yes it is
upvoted 4 times
...
...
ipindado2020
Highly Voted 4 years, 2 months ago
answer is correct
upvoted 8 times
...
saema
Most Recent 7 months ago
Selected Answer: C
c is correct-train-test-split
upvoted 1 times
...
Asaini125
1 year ago
Selected Answer: C
Yes, C is correct
upvoted 1 times
...
Vanessa23
1 year, 3 months ago
Training and validation datasets
upvoted 1 times
...
zellck
1 year, 7 months ago
Selected Answer: C
C is the answer. https://learn.microsoft.com/en-us/azure/machine-learning/component-reference/split-data?view=azureml-api-2
upvoted 1 times
...
lcssilva
1 year, 8 months ago
caiu no exame do dia 16/06/2023
upvoted 2 times
...
rdemontis
1 year, 8 months ago
Selected Answer: C
correct answer, in order to have a reliable test you need to use a different set of data
upvoted 2 times
...
ydu7312
2 years, 9 months ago
C is correct
upvoted 3 times
...
x_nodes
2 years, 9 months ago
Splitting the data for 1. Training the model. 2. Evaluating the model.
upvoted 2 times
...
baciga
2 years, 10 months ago
Selected Answer: C
C is correct
upvoted 1 times
...
eham757
3 years ago
Selected Answer: C
C is correct
upvoted 2 times
...
Lenore
3 years, 1 month ago
Selected Answer: C
C. to test the model by using data that was not used to train the model
upvoted 1 times
...
Marski
3 years, 2 months ago
You lose statistical power by estimating on a subset n like 50 percent of original N. Thats the price you pay for splitting data. For example a normally independently distributed (n.i.d) x has an estimator of arithmetic mean X whose variance inversely related to N. Bigger sample is better for accuracy of a simple arithmetic mean.
upvoted 1 times
...
IrinaWeiss
3 years, 6 months ago
Was on exam 30.07.21
upvoted 1 times
...
Chaz79
3 years, 7 months ago
C. to test the model by using data that was not used to train the model is correct
upvoted 3 times
...
TariqNawaz
3 years, 8 months ago
Answer is correct
upvoted 1 times
...
Load full discussion...
Community vote distribution
A (35%)
C (25%)
B (20%)
Other
Most Voted
A voting comment increases the vote count for the chosen answer by one.

Upvoting a comment with a selected answer will also increase the vote count towards that answer by one. So if you see a comment that you already agree with, you can upvote it instead of posting a new comment.

SaveCancel