New Year Sale 2026! 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

Microsoft AI-102 Exam - Topic 1 Question 13 Discussion

Actual exam question for Microsoft's AI-102 exam
Question #: 13
Topic #: 1
[All AI-102 Questions]

You are training a Language Understanding model for a user support system.

You create the first intent named GetContactDetails and add 200 examples.

You need to decrease the likelihood of a false positive.

What should you do?

Show Suggested Answer Hide Answer
Suggested Answer: A

Active learning is a technique of machine learning in which the machine learned model is used to identify informative new examples to label. In LUIS, active learning refers to adding utterances from the endpoint traffic whose current predictions are unclear to improve your model.


https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-glossary

by Mitsue at May 07, 2022, 11:32 AM

Limited Time Offer

25%

Off

Get Premium AI-102 Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

0/2000 characters
Submit Cancel
Ira
4 months ago
I’m not sure about that, isn’t it better to refine existing examples first?
upvoted 0 times
...
Valentin
4 months ago
Active learning could really improve accuracy over time!
upvoted 0 times
...
Gerald
4 months ago
Wait, why would adding more examples to GetContactDetails help with false positives?
upvoted 0 times
...
Edda
5 months ago
Totally agree, more examples for the None intent could help too!
upvoted 0 times
...
Samuel
5 months ago
I think adding a machine learned entity makes sense.
upvoted 0 times
...
Barrie
5 months ago
Adding examples to the None intent seems like it could clarify what the model shouldn't recognize, but I’m not entirely confident about that approach.
upvoted 0 times
...
Latrice
5 months ago
I think enabling active learning could help improve the model over time, but I can't recall if that directly decreases false positives.
upvoted 0 times
...
Keshia
5 months ago
I remember we discussed how adding more examples can help, but I'm not sure if it's the best way to reduce false positives.
upvoted 0 times
...
Ronny
5 months ago
I practiced a similar question where adding machine learned entities helped with intent recognition, so maybe option B is the right choice here?
upvoted 0 times
...
Alesia
5 months ago
Data locality seems like the clear winner to me. That's the option that directly addresses keeping the sensitive data close to the users, which is what the compliance team is requiring.
upvoted 0 times
...
Karl
5 months ago
This seems like a straightforward question about design patterns. I think the key is to identify the best approach for automating the Dispatcher's functionality using the Bulk Add Queue Items activity.
upvoted 0 times
...
Laurel
5 months ago
Okay, I've got this. User interaction is when the user directly engages with the system, so the answer has to be one of the options that involves the user taking an action. I'm confident I can nail this.
upvoted 0 times
...
Harrison
5 months ago
I think the three categories we studied were flow manufacturing, intermittent manufacturing, and something else... maybe project manufacturing?
upvoted 0 times
...

Save Cancel