Great summary!!

Very nicely explained ❤👍

Hey Data Science enthusiasts, this is the second part in understanding Diffusion Models. The Reparameterization Trick is also explained in this video.

Great Video. Tried t o follow the steps but did not get far. The actual version of the transformer library does not work with your code. Can you pls tell me which version you used, so i can adjust my environment. Thx

A great analogy to explain a complex and technical diffusion models topic with such an ease and relatable example. Thanks for this👍👍

Hello Data Science Enthusiasts. Did you know this fact? "The name diffusion takes inspiration from the well-studied property of thermodynamic diffusion. An important link was made between this purely physical field and deep learning in the 2015 paper Deep Unsupervised Learning using Nonequilibrium Thermodynamics (Sohl-Dickstein, 2015, arxiv.org/abs/1503.03585)".

In student_training_args you specified alpha is 1, is it intentionally to not account for loss_kd?

Best explanation of batch normalization👍

Very nice video… Simplified yet Informative …👌👍

Hello Data Science Enthusiasts, Chapters: 0:00 Introduction to Batch Normalization 0:47 Why Normalization is required? 1:20 Unstable Neural Networks, Vanishing and Exploding Gradient Problem 1:49 Batch Normation 2:49 Important Papers and References 3:54 Implementation of Batch Normalization in Python 📌 Code: github.com/DiveshRKubal/Machine-Learning/blob/master/batch_normalization/Batch_Normalization.ipynb

📌 Code: github.com/DiveshRKubal/GenerativeAI/blob/main/GemmaLLM/Gemma_Implementation.ipynb

Did not knew the background story of name Gemma…good to know that.

Wow good tutorial. RAG is quite the topic and nice that you walked us through an example

Hey! This was a beautiful tutorial and helped me out tremendously in my own personal project. Thank you!

Bro, if we increase the epochs, will reconstructed images deviate from the shirt image?

Hello Data Science enthusiasts, I have uploaded the code to GIT Repository. 📌 Code: github.com/DiveshRKubal/Retrieval_Augmented_Generation/tree/main/rag_custom_chatbot

Greate video!

interesting bro

Thanks! I find it a very nice tutorial in autoencoder implementation in TF; somewhat similar to what DeepLearningAI do on Coursera in their advanced tensorflow course.

Go in more depth lol VAE's are not something you can just learn with 9 minutes video.. Can you recommend best resource to learn VAE from please?

Hello great video, can you share the Colab notebook?

❤

Excellent video and I joined as a sub. Like this style of going thru the various architectures and the use case. Maybe you can also update it with GPT 4 since it’s new out there.

There is a confusion. Why you did not include language models which are also part of GENERATIVE AI

Yeah so many words like embeddings are used with no context

The main takeaway is sensitvising decoder to the joint distribution...cool.great video thanks

This was very insightful and thoughtful video. Great effort in highlighting these AI applications

Really good explanation

HI! I appreciate to upload this video. Can this code be used on any model? I have all ready training model!

i am confused.how i use my dataset in this code?

💀 bhai 200 error hau 😐

bohot error hai bruh🫠🥲

Sir, many channels are here in English. Please, make video in hindi and use simple language because thought the subscriber is low but in them one change their life.

thank you!! keep it up

The implementation cab be found at - github.com/DiveshRKubal/GenerativeAI/blob/main/Generative_Adversarial_Networks/DCGAN_(Deep_Convolutional_GAN).ipynb

Thanks a lot. do you have in-depth explanation/tutorials for each of these? what should you do when your language model doesnt exist on HF? How should you go about adding one?

Where can i get the Google collab code ??

for the algo

Can you train your model own transformer or I port from hugging face buddy?

Good video !

As usual the best description of VAE, @04:26, you said it develops mean and variance(its log) for each dimension. Does it refers to each channel of image . Also what is need for z_sigma and epsilon. 1. Is Mean and Variance not enough

Your video is wonderful!You did save my life ,thanks!😀

Good Video clarifying VAE

Very well explained

thank you sir ! Fantastic method of explanation

sir amazing method of teaching

Possible to do this with zephyr model.(mistral model) ?

This is fantastic 😍

Hello everyone, Hope I was able to simplify Generative Adversarial Network using this story. 0:00 Introduction to Generative Adversarial Networks 0:19 The Start of GAN Story 0:44 Let me introduce Generator and Discriminator 1:09 Alice deciding to use Generator and Discriminator to generate Paintings 1:30 Discriminator catches Fake Generated Paintings by Generator 2:06 Training of Generator and Discriminator based on Feedback 2:21 A Happy Alice 2:42 Powerful Generator and Discriminator 3:04 History of GANs - Ian Goodfellow's 2014 Research Paper - Generative Adversarial Nets 3:46 Architecture of Generative Adversarial Networks Please give me a feedback so I can improve in next tutorial videos...

I just found this video and it's very good. I'm currently trying to understand when to use what type of model. Looking at Huggingface is just overwhelming. That's where this video jumps in and provides an excellent overview of the major models. I wish there would be a similiar video explaining the various pretraining objectives.