CertNexus AIP-210 Exam - Topic 5 Question 35 Discussion

Actual exam question for CertNexus's AIP-210 exam

Question #: 35
Topic #: 5

In a self-driving car company, ML engineers want to develop a model for dynamic pathing. Which of following approaches would be optimal for this task?

ADijkstra Algorithm

BReinforcement learning

CSupervised Learning.

DUnsupervised Learning

Show Suggested Answer

Suggested Answer: C, E

Lasso regression and ridge regression are both types of linear regression models that can handle high-dimensional and categorical data. They use regularization techniques to reduce the complexity of the model and avoid overfitting. Lasso regression uses L1 regularization, which adds a penalty term proportional to the absolute value of the coefficients to the loss function. This can shrink some coefficients to zero and perform feature selection. Ridge regression uses L2 regularization, which adds a penalty term proportional to the square of the coefficients to the loss function. This can shrink all coefficients towards zero and reduce multicollinearity. Reference: [Lasso (statistics) - Wikipedia], [Ridge regression - Wikipedia]

by Scarlet at Dec 10, 2024, 03:31 PM

Limited Time Offer

25%

Off

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

Contribute your Thoughts:

Submit Cancel

Dominga

10 months ago

Reinforcement learning has proven effective in similar scenarios.

upvoted 0 times

...

Sharita

10 months ago

Wait, unsupervised learning? That seems risky for driving!

upvoted 0 times

...

Belen

11 months ago

Supervised learning might not adapt well to new situations.

upvoted 0 times

...

Leigha

11 months ago

Dijkstra's algorithm is too rigid for real-time changes.

upvoted 0 times

...

Bettina

11 months ago

I think reinforcement learning is the way to go for dynamic pathing!

upvoted 0 times

...

Kattie

11 months ago

Unsupervised learning doesn't seem relevant here at all. I think we practiced similar questions, and the focus was on learning from feedback.

upvoted 0 times

...

Georgiana

12 months ago

Supervised learning seems more about prediction than pathing, right? I feel like it wouldn't handle dynamic changes well.

upvoted 0 times

...

Kanisha

12 months ago

I think reinforcement learning could be a good fit since it adapts to changing environments, but I can't recall if we covered that in depth.

upvoted 0 times

...

Justine

12 months ago

I remember studying Dijkstra's Algorithm for shortest path problems, but I'm not sure if it's the best for dynamic situations.

upvoted 0 times

...

Fernanda

12 months ago

I'm leaning towards supervised learning. If we have enough data on safe driving patterns, we could train a model to predict the optimal path in different scenarios. Reinforcement learning might be overkill for this use case.

upvoted 0 times

...

Idella

12 months ago

Definitely go with reinforcement learning. The car needs to learn how to adapt to changing road conditions and make autonomous decisions, which is exactly what RL is designed for.

upvoted 0 times

...

Kimbery

12 months ago

I'm a bit unsure on this one. Dijkstra's algorithm is good for finding shortest paths, but I'm not sure if that's the best fit for a self-driving car. Maybe supervised or unsupervised learning could work better?

upvoted 0 times

...

Deonna

1 year ago

I think reinforcement learning would be the best approach here. The car needs to learn how to navigate dynamic environments and make real-time decisions, which is a perfect fit for RL.

upvoted 0 times

...

Susana

1 year ago

Reinforcement learning, huh? I wonder if the car will get a snack every time it successfully avoids a pothole. That would be one well-fed self-driving vehicle!

upvoted 0 times

Amie

1 year ago

C) Supervised Learning.

upvoted 0 times

...

Laura

1 year ago

B) Reinforcement learning

upvoted 0 times

...

Romana

1 year ago

A) Dijkstra Algorithm

upvoted 0 times

...

Desmond

1 year ago

Dijkstra algorithm? What is this, a trip planning app? Self-driving cars need a more dynamic approach, and that's where reinforcement learning shines.

upvoted 0 times

Hannah

1 year ago

Exactly, supervised learning and unsupervised learning wouldn't be as effective in this scenario.

upvoted 0 times

...

Rima

1 year ago

Dijkstra algorithm is more for finding the shortest path, not for dynamic decision-making.

upvoted 0 times

...

Anissa

1 year ago

I agree, it allows the car to learn from its environment and make decisions in real-time.

upvoted 0 times

...

Timmy

1 year ago

Reinforcement learning is definitely the way to go for self-driving cars.

upvoted 0 times

...

Dominque

1 year ago

Unsupervised learning? Are you kidding me? The car needs to learn how to navigate the roads, not just cluster data. Reinforcement learning is the obvious choice for this task.

upvoted 0 times

Shaun

1 year ago

I agree, the car needs to learn from its actions to navigate effectively.

upvoted 0 times

...

Sharita

1 year ago

Reinforcement learning is definitely the way to go for dynamic pathing.

upvoted 0 times

...

Kanisha

1 year ago

I think Supervised Learning could also be a good option, as it can learn from labeled data.

upvoted 0 times

...

Cyril

1 year ago

Supervised learning? Really? I don't think labeled training data would be comprehensive enough to cover all the scenarios a self-driving car might encounter. Reinforcement learning is clearly the best option here.

upvoted 0 times

...

Nicolette

1 year ago

I disagree, I believe Dijkstra Algorithm would be more suitable for dynamic pathing.

upvoted 0 times

...

Deonna

1 year ago

Reinforcement learning seems like the way to go for dynamic pathing in self-driving cars. It can help the model learn and adapt as it encounters new situations on the road.

upvoted 0 times