Відео

Incredibly useful!

Now, let's do it iteratively :)

Thank you for this video. Love the content and explanation. Just one comment on the recording itself. I don't know what it is but i see a lot of videos with this effect where the video cuts like every two seconds. my brain hurts when it happens so many times.

do you have any ML book recommendations using pytorch?

Great video!! How are the initial 1M videos selected? is it based on category, etc and newness & trending factor? Whenever a user clicks on a video, we see recommendations in just a second. I don't think it's practically possible to select 1M videos for each video clicked by user and then do all the analysis in real-time. Is it possible that for each video when uploaded, it already identifies and stores ids & metadata of the possibly going-to-be recommended 500 videos? Whenever a user selects a video, it joins his attributes & past videos with this 500 videos quickly?

Your calculation of queries per second is incorrect. There are 2 billion monthly active users, each user watches X videos per month. If you divide 2X by the number of seconds in a month, you will get the average QPS.

brilliant

Could anyone here help me out with similar ML System Design problems that Google/ Meta might ask in their interviews?

For someone not yet deep into ML, it's pretty good info as well.

I loved your way of way of teaching. Would be great to see more paper review like this

Wow 👏

Wow Amazing Thank you!!!!

Thank you! I thought it mean at most K of a single character xD

What do you study bro?

Thank you. After seeing your lecture I just solved LeetCode "141. Linked List Cycle" problem by only one submission. Awesome.

@ML Tech Track how do u modify this code to return the substring with the same condition.

The scaling/load calculation looks wrong at many levels! 700 users watching youtube or being recommended next video at any given second? Grossly incorrect number

It is interesting and very helpful!! Please do post more such ML paper reviews..glad i came across your vid. Clear and detailed explanation 👏👍

scholar score = scalar score

🤜🏼🤛🏼 nice work

ngl, the mathematical proof (or intuition behind it) is the most important part of a problem like this. Leaving it out doesn't make any sense. Intuitively, if the cycle started at the head, moving forward the length of the cycle would bring you back to the start of the cycle. If the cycle starts at head.next, moving forward the length of the cycle would bring you one step away from the start the of cycle. If the cycle starts at head(.next k times), moving forward the length of the cycle would bring you k steps away from the start of the cycle.

I do not get the part where you saying the line 30 to 33

Clear like water bro!

very good video .. impressive

I would like my time back

Well explained. Thank you for the video

How much u charge for making a video recommendation system for Android app?

The improvement is not significant at all.

so helpful, i really like how you did that pseudocode while explaining the pattern!

Best explanation I have seen in ML system area! Thanks!

Great overview. Thanks!

why second approach time com is 9!^9 not 9!*9 ?

Clear, simple, direct illustration 👌 Thanks

Could you explain how the logistic regression or the random forest would narrow down the list of candidates in the funnel?

Small Improvements: cycle_len += 1 for each iteration of the original while loop, so you immediately know the meeting point once we have broken out of the while loop and determined cycle_len != -1: slow = head (fast already equals the original meting node) <perform the next for loop, looking for when they meet> This will save you two unnecessary for-loops! Otherwise great explanation :)

Hmm ok so algorithms with scaling runtimes in order to operate on large to small amounts of data, makes sense. Does anyone know how that first "simply query" would go from billions of videos to one million?

Nice job. Thanks.

thank you, it is so usefull!

Woah... Neat explanation... thankyou

trying to find the dataset and code .. hihi

Thank you for the clear and concise explanation! It would be great if you continued such videos for ML Design Interview prep on other topics! Looking forward to it!

Thanks!🙏🏾

Very useful video. Thanks!

So 2 bio people watching 1 sec per month, huh??

Could you also do scaling analysis - like how this model would scale and deploy this model to be able to serve potentially >700 requests/sec? Thanks for the amazing content!

Nice overview. Thanks!

Hi 👋; Glad to hear you . I have to learn basic forms of your course. I try to learn with you .

😘👍