Відео

Thank you so much!!!!!!!!!!!!

This is the best explanation of likelihood function. thank you so much for the video.

Tremendous!

Excellent videos! Great graphing for intuition of L1 regularization where parameters become exactly zero (9:45) as compared with behavior of L2 regularization.

i am starting from 1st video, will escape topic i remember, and finish all his course. duirng holidays

nice video

corny sounds shit

thank you so much that was so helpful

Excellent! Thanks :)

✨Quiiizz Timmmeeee✨

Great video! It's funny you mentioned unsupervised learning at the start but didn't mention LLMs

nice work ! how much data(parallel corpora) is sufficient or atleast required for machine translation ?

great explanation, could you make a video about Direct Preference Optimization (DPO)?

Amazing explanation 🎉🎉🎉🎉

I swear the quiz time backing track is from Hedgewars 😄

I did all Calcs in Engineering school - partical differential equations (PEDs) being the most brutal - but its crazy how people thought of this shit. Blows my mind....

I love the downplayed "Quiz time" :D

Thanks!

Amazing video! Thank you.

I think your code is not correct, LayerNorm will not be over the batch. Try and think what it means to take normalisation over the batches. For a layer norm each entity of the batch is unique, and each should be normalised across the layer of the MLP (essentially everything is MLP).

May be wrong I am not an expert but isn’t the Bellman equation supposed to add the reward of the S1 not S2?

Nicely explained! I got better understanding of this, could you also include some examples which give some feel about the calculations...

It should have been plain vanilla RNNs that originated in 1990s, not LSTM which should have been developed on top on RNNs later.

where to det your slides?

Excellent job. There is way too much "mysticism" around neural networks. This shows clearly that for a classification problem all the nerual net is doing is creating a boundary function. Of course it gets complicated in multiple dimensions. But your explanations and use of graphs is excellent

what makes these different than tokenizers

Dense but informative.

I think the start token, padding token and end token should have some different name other that just empty string in the vocabulary as otherwise while initialising a language_to_index dictionary from vocabulary the last index having the value of empty string is overwriting all the previous indices with empty string.

👏👏👏❤️

oh, this is much better, update your weights:)

Thanks! Excellent videos!

I less like your channel since you have an obvious overuse of terminology instead of an explanation, which looks to me like intentional supercilious upscaling of the entrance threshold

A bigger issue is “Arabic Numbers” being actually Hindu. With the concept of zero.

Can you please make a video that showcases how we can generate custom word embedding on a custom dataset from scratch? Without using anything pre-built? Say IMDb dataset? and then later load them to train a classification model?

greek. yogurt.

mind BLOWING..lucky enough to find your lectures

Great lecture..Thank you so much for this video.. Great resource..

Your vides deserve more recognition. Thank you for helping out sir. Looking forward to keep learning from you.

Amazing work! congratz!

Hochreiter, S., & Schmidhuber, J"urgen. (1997). Long short-term memory. Neural Computation, 9(8), 1735-1780.

The Best Creator for DS I've found, Thanks a lot!

good course, but I don't get how the data collected for Zi, because Zi = 1 when the sample (in treatment group and convert) OR the sample (in the control group and not convert). Persuadable should be the 'AND' between the above relationship, is it?

i literally understand all of it, thank you so much

Thank you for providing these papers

For Quiz Time 1 at 3:47, Shouldn't the answer be B: 0.5 sq units. I think the entire premise is that you know the area of a region, you know the ratio of balls dropped in both regions, and the ratio of balls dropped equals the ratio of area. Therefore you can use this information to determine the unknown area.

can I get these slides?

Thank you for this fantastic tutorial.

Are you an Indian?

Very Well explained by you sir,It helped alot

8:09 I stopped watching when he thinks 1.5 is greater than 2.1 lmao