วีดีโอ

Great video. Thank you!

Thank you Sir, But I am having some problems at 2:35, can you please tell me the prerequisites for understanding this. Or any one who is watching and understand this part

The best!!

This was amazing. Please put out more content

Thanks! Watching your videos. Great.

u might be the goat

Thank you it was clear and transparent

Really appreciate you speeding thru the writing parts!!

Wonderful explanation... thanks for putting this online

Thanks!

It's a really great explanation. Thank you so much!

I cannot believe I found this hidden gem channel till now! Thank you for the clear and concise walkthrough of a plethora of CS topics, Mr. Rhodes! Watching them feels like ASMR!

This is from the book Understanding the Linux Kernel by Daniel Bovet and Maarcos Cesati , chapter 2 memory addressing

So in 4/5 level paging do we keep flags on each paging directory?

Why so underrated... Great and detailed explanation, came from your video series about Style Transfer.

Thompson Jennifer Lee Brenda Anderson Jeffrey

Huge respect sir.

Hernandez Shirley Wilson Amy Hall Sharon

Thank you for the clear explanation.

Definitely deserves more likes

Such a great explanation

why the video is using pictures instead of the video, it looks strange

WOWW an extremely clear explanation. You are an expert teacher...!!! Thank you soo muchhhhhh

This is the best video explaining about Resnet I've ever seen. Thanks for sharing.

Pretty neat! Watched all the 7 videos of this playlist and I think these are the best in this subject.

can you share the configuration of the debugger you are using?

Hi, Neil. I love the clear board setup. Thank you for putting these lectures online!

Wonderful course, Might I ask where can I get the source code which during the lecture that you demonstrate the attention variation through the image to text.

For those following this in a playlist, next video might be #7 (Overfitting-underfitting). After that resume the list order.

Wonderfully explained, thanks a lot!

Hi sir, I have been watching your videos for quite a while. Really insightful. I have a doubt in this video. Is 'T' (the temperature constant) multiplied to the y-cap or divide it? From the other sources that I have seen, scaled_logits = original_logits / T. Then, if the T > 1 the model becomes more creative and if the T < 1 then the model becomes consistent which is opposite to what you have said. Kindly provide your view on this.

Thanks for the wonderful video. I think there may be a slight error w.r.t to your commentary about x86s reordering loads. x86 memory model does not reorder loads w.r.t to loads. they only reorder store->loads due to store buffers so in the examples you provided, an x86 would not require a read side barrier.

This is the best explanation, I have found through out the entire internet. The trade-off of top-P vs top-K explanation is amazing! Thanks, a lotttt for making this such a goldmine public.

Thank you so much for your explanation! Much appreciation for your sharing.

This is what I looked for. My thanks

Jennifer Lopez 😆😆

This is a truly artful breakdown of the mechanisms involved. Rare are such teachers in saturated fields like ML.

Thank's a lot my man, very concise and informative with no wasted time.

Man i am new graduate and i did everything wrong with my first job offer

YOU ARE A LEGEND SIR!

wonderful

how you define the filters?

what a great presentation.

You are an absolute legend.

but how does it get to know the upper bound, how will it know the E is the process that is directly up side of C

Amazing video as always. Thanks Dr. Rhodes!

one of the best explanation

I'm following you for some time and I loved how u make ur videos .... Thanks for all the knowledge u provide.

Can you use both top_p and top_k? With llama you can set both

Have to deal with VMs and qcow2 files. Your visual presentation is very helpful. Thank you.