Відео

Thanks Ahlad, I really liked your explanation of LSTM and GRU please continue to make videos on seq-2-seq models, Transformers, MoE

Sir how adjacency matrix can feed to machine learning

Sir, thanks for the video. I have further modified your code to enhance the accuracy

thanks ! great explanation

23:00

sir where are the links and code

@AhladKumar pls help

@ Ahlad Kumar I subscribed for premium content but your 7 hidden videos are not showing to me

23:21 How to know how many flattened layers should be there..? I mean, why 120 & 84 FCs..?

I join channel but i don't have access to all reinforcement learning videos

I join the channel with 599 but i am not able to access the content

By P(x), do u mean P(~x){i mean P(telta x)}? 4:25

Hat's off to you and the people behind this work. Absolutely amazing

can anybody explain me what is noise input to generator and why we use it

🤔

Thank you for sharing!

Hey everyone, please note that sir made a mistake at 28:00, mistake that he clarified in next video . The expectation terms will also include minG and maxD on RHS of equation

Please direct 1 or 2 more example for finding gm based on seeing the resistance in the Branches ..

In the last configuration you told, why CAN'T we take Rout as Rout of source degeneration resistance , or 2 stage cascode resistance

I think that in 0:48 you meant to write and say that the role of the generator is to "...can fool the *discriminator* " instead of the generator.

LSTM architecture is more complex than RNN architecture, but formulas for gradient look much easier than for RNN. I think your formulas are incorrect. For example: dL / dWi = .....dit/dwi, and you write that dit/dwi = ht-1, but ht-1 is also depends on wi, because ht-1 = Ot-1*tanh(ft-1 * ct-2 + it-1 * gt-1), where it-1 also pedends on on wi

A huge amount of work done by you. Thanks teacher!!!

Thank you very much for math explanation. It was very important for me!!!You have simplified it to the smallest detail, now i can implement it in my code! Thanks!!!

Thank you!!!

💯💯💯

God bless you brother

Could you share this code?

if the decoder generates based on the condition, what is the point of the Z? does it also mean conditions C dominate the influence on the decoder then?

this is gold.

Best graph neural network video

Link of the code?

just perfect explanation

Very nice

Hi Ahlad, your explaination is awesome. Thanks for posting the videos. It would be greate if you can keep posting new lectures about the most recent DL technologies, such as transformers and so on.

great

amazingly explained.....understood the notations so so easily. its easy to read a research paper related to GAN comparitively better.

sir any video which explains latent space easily?

sir wht do u mean by l2 nor , l1nor etc

NN not enough for images because: 1. every pixel has some correlation with neighbouring pixels but 1D representation takes pixels row wise and so the model can't properly learn this correlation 2. too many parameters to optimize cause every image has too many pixels 3. translation invariance: if you move the object in the image say in to the right, NN will think they're different

very interesting but boring...

Sir, kindly guide what we have to do in order to test discriminator model of our GAN.

Thank you for a great explanation. Is there a book covering this material

💖💖

💖💖

💖💖

exeellent lecture series. do you mind sharing the Google colab? Thanks

You are great

perfect explaination

@Ahlad Kumar Sir, Thank You for making these amazing lectures. It is the best lecture and detailed lecture on AutoEncoder and its series. Thank You once again. _/\_