วีดีโอ

awesome video thanks

👍👍👍👍👍👍👍👍👍👍👍👍👍👍

Incredible waste of time. The video doesn't even attempt to explain why would the vectors of each matrix represent different categories.

excellent explanation, as a data science from a biology background this really helped

Your class is good 🙏🏼

You’re my guardian angel

Does this enable older designers to show the AI an image of their hand-drawn designs and get a STEP or IGES encoded 3D file for use in applications? I am looking for a use case where mixed reality headset cameras can capture image information and process it into a shareable 3D format!

4:37 Say if the p(X=4)=0.5 What is the interpretation of this exact statement? Could it be that the probability of x occurring arbitrarily close to 4 is 50%?

Thank you

You’re my guardian angel

AHH!!! I’ve been trying to find more content from you since you left Talking Machines for years!! So glad I finally found this! I wonder how to fix the squeaky pen 🤔

Very nice intuition video with the perfect amount of math!

Really well explained

I'm wondering about the importance sampling. If I understand correctly, we need both pi(x) and q(x) pdfs to use IM. But shown in the previous video "COS 302: Pseudo-Random Numbers", we can draw samples for any arbitrary pi(x) using the CDF + uniform rand trick. In that case, why wouldn't we use the trick with pi and draw from pi directly? I know there are cases where IM is useful, especially in ML/RL for learning or estimating some expectation from _offline data_ . But I can't see the reason why we choose to _sample_ from q instead of pi when we have both pdfs. What am I missing?

Underrated channel

Great explanation !

Very beautiful. Thank you.

Just brilliant.

Awesome. Thank you.

Excellent explanation!! Thanks

How does this whiteboard works?

Thanks

Is the ground truth set weighted by a average, max, common, rare, gravity, edges, node distribution or what?

Thank you for the very clear explanation! I never took a stats class, so online resources like this help me survive upper division CS and ME classes. Much needed for fluids labs and speech processing!

Thanks so much, I like how you explain

Thanks so much, nicely explained!

PLEASE use another pen, I can't finish the video. Great explanation anyways!

Thanks a ton!! It wasn’t only intuitive, you explained what is in the book with the exact notations which makes it easier for me to go back and solve problems there.

Amazing lectures!! I assumed that i will flunk my class before I watched these. You somehow make it sound simple. Thanks a lot

I frickin love you man.

These videos are so amazingly awesome!!!

loved it thanks !

Thankyou so much 💯

astonishing video Intelligent Systems Lab. I shattered that thumbs up on your video. Keep up the very good work.

Succinct.

As a data engineer from a non-CS background, it's one of the most helpful materials I found on the internet for linear algebra. It gives a great intuition to understand the math and real-world examples. Huge thanks!

I like your explanation, but the sound of your pen hitting the board is extremely disturbing!

Amazing vid!

True that! Some Jupyter examples would ve made it complete :)

Thanks 👌👌👌👌👌👌👌

this is awesome I just need to find the time to watch all these and take notes

The explanation is simple and elegant, thank you so much for making this brilliant video! I finally understand Bayes Theorem and marginal distribution!

So well done! And the graphic design of 3B1B helps a lot to maintain continuity with Grant's content so that even new viewers aren't disoriented by different visuals.

very good video

Please help me, how can I synchronise the animations with the audio? What I am thinking is that I should give long pauses by using `self.wait()` and then trim the video according to the narration. I suppose this is not the best method, please share your method if you have better one.

This is a great topic.

This is wonderful. Thanks!