S.N |
Topic |
Slides |
External References |
1. |
Introduction |
Slides |
.. |
2. |
Backpropagation and Regularization methods for Deep Models |
-
Notes -1
-
Notes-2
| Backpropagation |
3. |
Variational Autoencoder |
-
Notes
| VAE- Tutorial |
4. |
Variational Autoencoder-II |
-
Lowerbound derivation-Notes
-
Recorded Lecture
|
-
VAE-PPT
VAE-PPT-II |
5. |
Introduction to GANs |
-
Standard GAN Loss function formulation
-
Slides
-
Recorded Lecture
|
-
GAN Standard Paper by Ian Goodfellow
-
GAN-Tutorial
|
6. |
GAN theory and WGAN - Motivation |
-
Standard GAN theory
-
Slides
-
Recorded Lecture
|
-
Slides - TOWARDS PRINCIPLED METHODS FOR TRAINING
GENERATIVE ADVERSARIAL NETWORKS
-
TOWARDS PRINCIPLED METHODS FOR TRAINING
GENERATIVE ADVERSARIAL NETWORKS
Paper
-
Wasserstein GAN
|
7. |
WGAN-GP, SNGAN and PGGAN (Variants of GAN frameworks) |
-
Notes
-
Slides
-
Recorded Lecture
|
-
Nice blog - SNGAN
-
Nice blog - WGAN-GP
-
WGAN vs WGAN-GP
-
WGAN-GP Paper
-
SNGAN Paper
-
Nice blog - PGGAN
-
PGGAN Paper
|
8. |
Evaluation Metrics - FID score and Inception Score |
- -
|
-
FID and Inception Score
|
9. |
Cycle GAN - Image to Image Translations |
-
Notes
|
-
CycleGAN
|
10. |
Introduction to Graphs and Graph Neural Networks |
-
Slides
|
-
GNN
|
11. |
GCN and GAT |
-
Slides
-
Notes
|
-
GCN and GAT
|
12. |
GCN and GAT - II |
-
Notes
|
-
GCN and GAT
|
13. |
GraphRNN |
-
Graph RNN Slides, credits:CS224w
-
Graph RNN blog
| |
15. |
Image Captioning Before "Attention is all you need" and DRAW Model |
-
Slides from NPTEL - Credits to Prof. Vineeth Balasubramaniam, IITH Link
| |
15. |
Transformer - Self attention and Multi-head attention |
-
Slides from NPTEL - Credits to Prof. Vineeth Balasubramaniam, IITH Link
-
Encoder Explained Clearly- Blogpost Link
|
16. |
Decoder - Transformer |
-
Slides from NPTEL - Credits to Prof. Vineeth Balasubramaniam, IITHlink
-
Decoder Explained clearly - Masked Attention
link
|
17. |
BERT Model |
-
BERT Model Vs Word2Veclink
-
External Reference
Link
-
External Reference -II
Link
|
18. |
GPT |
-
What is GPT Model (very nice blog)
-
BERT and GPT Model
|
19. |
- LLAMA
- Multi Head Attention Vs Multi Query Attention
- Cache Aware Memory Access
|
-
LLAMA2_slides
-
MultiQueryAttention vs MHA
|
20. |
CLIP Model and Multimodal Pre-training |
-
Vision-Language Models (upto 13th slide)
-
CLIP
|
21. |
Diffusion Models |
-
Diffusion Models
|
21. |
Stable Diffusion |
-
To be updated
|