CertNexus AIP-210 Exam - Topic 2 Question 7 Discussion

Actual exam question for CertNexus's AIP-210 exam

Question #: 7
Topic #: 2

An AI system recommends New Year's resolutions. It has an ML pipeline without monitoring components. What retraining strategy would be BEST for this pipeline?

APeriodically before New Year's Day and after New Year's Day

BPeriodically every year

CWhen concept drift is detected

DWhen data drift is detected

Show Suggested Answer

Suggested Answer: B

A support-vector machine (SVM) is a supervised learning algorithm that can be used for classification or regression problems. An SVM tries to find an optimal hyperplane that separates the data into different categories or classes. However, sometimes the data is not linearly separable, meaning there is no straight line or plane that can separate them. In such cases, a polynomial kernel can help improve the prediction of the SVM by transforming the data into a higher-dimensional space where it becomes linearly separable. A polynomial kernel is a function that computes the similarity between two data points using a polynomial function of their features.

by Arlette at Oct 20, 2023, 09:38 PM

Limited Time Offer

25%

Off

Get Premium AIP-210 Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

Submit Cancel

Marsha

3 months ago

D could be important too, especially with changing trends!

upvoted 0 times

...

Jill

4 months ago

A is a good idea, but it might not be enough.

upvoted 0 times

...

Paola

4 months ago

Wait, can you really detect concept drift? Sounds complicated!

upvoted 0 times

...

Keena

4 months ago

I disagree, B seems more consistent for yearly resolutions.

upvoted 0 times

...

Odette

4 months ago

I think option C makes the most sense for retraining.

upvoted 0 times

...

Tamra

4 months ago

I lean towards option B since it suggests a regular schedule, but I wonder if it’s enough without monitoring for changes.

upvoted 0 times

...

Theresia

5 months ago

I practiced a similar question where timing was key. I feel like option A might be too rigid for a dynamic system like this.

upvoted 0 times

...

Xochitl

5 months ago

I'm not sure, but I remember something about data drift being important too. Maybe option D could be relevant?

upvoted 0 times

...

Horace

5 months ago

I think option C about concept drift makes sense because people's resolutions can change over time, right?

upvoted 0 times

...

Glendora

5 months ago

Option B, retraining periodically every year, seems like a good baseline approach. That way we can stay on top of changes without relying on potentially unreliable drift detection.

upvoted 0 times

...

Heike

5 months ago

I'm leaning towards option C - retraining when concept drift is detected. Since the system is recommending New Year's resolutions, the underlying data and patterns could shift significantly over time, so we'd want to be responsive to that.

upvoted 0 times

...

Marcos

5 months ago

Hmm, I'm a bit confused. Does the lack of monitoring components mean we can't detect concept or data drift? That could impact the best retraining strategy.

upvoted 0 times

...

Phuong

5 months ago

This seems like a tricky one. I'll need to think carefully about the different retraining strategies and how they might apply to this specific scenario.

upvoted 0 times

...

Virgie

5 months ago

Okay, I think I've got this. Since R-LFA and TI-LFA are both enabled, R1 will use an R-LFA path that doesn't coincide with the post-convergence path. Option B looks like the right answer.

upvoted 0 times

...

Yan

5 months ago

I think the REST API is the way to go here. It's the most modern and flexible option for accessing the Attribute Group schema.

upvoted 0 times

...

Jennifer

5 months ago

I've got this! The IP address and netmask of the host via the management port are the two parameters that can be set during the initial BIG-IP system configuration. Easy peasy.

upvoted 0 times

...

Trinidad

10 months ago

I'm just hoping the AI doesn't start suggesting resolutions like 'become a professional couch potato' or 'learn to speak fluent gibberish'.

upvoted 0 times

Tiara

10 months ago

B) Periodically every year

upvoted 0 times

...

Irving

10 months ago

C) When concept drift is detected

upvoted 0 times

...

Eleonora

10 months ago

A) Periodically before New Year's Day and after New Year's Day

upvoted 0 times

...

Quentin

10 months ago

Haha, imagine an AI system recommending resolutions like 'eat more ice cream' or 'nap for 12 hours a day'. Definitely need to keep a close eye on that concept drift!

upvoted 0 times

Sharen

10 months ago

Kayleigh: Agreed, we need to make sure it's giving out helpful recommendations.

upvoted 0 times

...

Kayleigh

10 months ago

User 2: Definitely! We should retrain the AI system when concept drift is detected.

upvoted 0 times

...

Hershel

10 months ago

User 1: Haha, that would be funny! 'Eat more ice cream' as a resolution.

upvoted 0 times

...

Carey

10 months ago

D) When data drift is detected could also work, but concept drift is more important for this use case. The system needs to understand the changing meanings of 'New Year's resolutions' over time.

upvoted 0 times

...

Tammi

11 months ago

I agree, C is the way to go. Retraining based on concept drift will ensure the system stays aligned with the user's evolving needs.

upvoted 0 times

Pete

9 months ago

I agree, C is the way to go. Retraining based on concept drift will ensure the system stays aligned with the user's evolving needs.

upvoted 0 times

...

Benton

10 months ago

C) When concept drift is detected

upvoted 0 times

...

Georgeanna

10 months ago

B) Periodically every year

upvoted 0 times

...

Roosevelt

10 months ago

A) Periodically before New Year's Day and after New Year's Day

upvoted 0 times

...

Carmen

11 months ago

C) When concept drift is detected seems like the best option. Monitoring for concept drift is crucial for an AI system that makes recommendations, as the user's preferences and the relevance of the resolutions can change over time.

upvoted 0 times