Syllabus

Note: The detailed course material can be modified.

For the Cont. Case, we will use the slides from the previous lecture.

Lecture - 1. Tuesday: Introduction, 

Lecture -1. Thursday:  Generative Model, Introduction (steps to reach stable diffusion)

Lecture - 2. Tuesday:  Autoencdoer -1.1

Lecture - 2. Thursday: Autoencdoer -1.2

Lecture - 3. Tuesday: Holiday

Lecture - 3. Thursday: Autoencdoer -2.2

Lecture - 4. Tuesday:  Autoencdoer -3.1

Lecture - 4. Thursday: Autoencdoer -3.2

Lecture - 5. Tuesday: Holiday

Lecture - 5. Thursday: Holiday

Lecture - 6. Tuesday: Variational Autoencoder -2.1

Lecture - 6. Thursday: Variational Autoencoder -2.2

Lecture - 7. Tuesday: Variational Autoencoder -3.1

Lecture-7. Thursday:  Variational Autoencoder -3.2

Lecture-8. Tuesday: Test week

Lecture-8. Thursday: Midterm

Lecture - 9. Tuesday: Generative Adversarial Network -1.1

Lecture - 9. Thursday: Generative Adversarial Network -1.2

Lecture - 10. Tuesday: Generative Adversarial Network -2.1

Lecture - 10 Thursday: Generative Adversarial Network -2.2

Lecture - 11. Tuesday:  Generative Adversarial Network -3.1

Lecture - 11. Thursday:  Generative Adversarial Network -3.2

Lecture - 12. Tuesday: Autoregressive Model -1.1

Lecture - 12. Thursday: Autoregressive Model -1.2

Lecture - 13. Tuesday: Autoregressive Model -2.1

Lecture - 13. Thursday: Autoregressive Model -2.2

Lecture - 14. Tuesday: Diffusion -1.1

Lecture - 14. Thursday: Diffusion -1.2

Lecture - 15. Tuesday: (Latent) Diffusion -2.1

Lecture - 15. Thursday: (Latent) Diffusion -2.2

Lecture-16. Tuesday: Test week

Lecture-16. Thursday: Final Exam