In this course, we will cover topics which lie at the intersection of Deep Learning and Generative Modeling. We will start with basics of joint distributions and build up to Directed and Undirected Graphical Models. We will then make a connection between Graphical Models and Deep Learning by having an in-depth discussion on Restricted Boltzmann Machines, Markov Chains and Gibbs Sampling for training RBMs. Finally, we will cover more recent Deep Generative models such as Variational Autoencoders, Generative Adversarial Networks and Autoregressive Models.
INTENDED AUDIENCE: None
CORE/ELECTIVE: Elective
UG/PG: UG/PG
PREREQUISITES: Deep Learning
INDUSTRY SUPPORT: Google, Microsoft, Amazon, Adobe, IBM,
5935 students have enrolled already!!
ABOUT THE INSTRUCTOR:
Mitesh M. Khapra is an Assistant Professor in the Department of Computer Science and Engineering at IIT Madras. While at IIT Madras he plans to pursue his interests in the areas of Deep Learning, Multimodal Multilingual Processing, Dialog systems and Question Answering. Prior to that he worked as a Researcher at IBM Research India. During the four and half years that he spent at IBM he worked on several interesting problems in the areas of Statistical Machine Translation, Cross Language Learning, Multimodal Learning, Argument Mining and Deep Learning. This work led to publications in top conferences in the areas of Computational Linguistics and Machine Learning. Prior to IBM, he completed his PhD and M.Tech from IIT Bombay in Jan 2012 and July 2008 respectively. His PhD thesis dealt with the important problem of reusing resources for multilingual computation. During his PhD he was a recipient of the IBM PhD Fellowship and the Microsoft Rising Star Award. He is also a recipient of the Google Faculty Research Award, 2018.
COURSE LAYOUT:
Module 1 : A brief introduction to Directed Graphical Models Module 2 : A brief introduction to Markov Networks, Using joint distributions for classification and sampling, Latent variables Module 3 : Restricted Boltzmann Machines, Unsupervised Learning, Motivation for Sampling, Markov Chains, Gibbs Sampling for training RBMs, Contrastive Divergence for training RBMs Module 4 : Variational Autoencoders, Autoregressive models, GANs
SUGGESTED READING MATERIALS:
Deep Learning, An MIT Press book, Ian Goodfellow and Yoshua Bengio and Aaron Courville.
CERTIFICATION EXAM :
The exam is optional for a fee.
Date and Time of Exams: April 28 (Sunday) Morning session 9am to 12 noon; Afternoon Session 2pm to 5pm.
Registration url: Announcements will be made when the registration form is open for registrations.
The online registration form has to be filled and the certification exam fee needs to be paid. More details will be made available when the exam registration form is published.
CERTIFICATION:
Final score will be calculated as : 25% assignment score + 75% final exam score
25% assignment score is calculated as 25% of average of Best 6 out of 8 assignments
E-Certificate will be given to those who register and write the exam and score greater than or equal to 40% final score. Certificate will have your name, photograph and the score in the final exam with the breakup.It will have the logos of NPTEL and IIT Madras.It will be e-verifiable at nptel.ac.in/noc.
