Prereqs: 6.046 or equivalent; 6.042/6.041/6.008 or equivalent; 6.867 or equivalent
Schedule: MW2:30-4, Room 54-100
This subject qualifies as an Artificial Intelligence concentration subject.
Recent advances in deep learning have enabled us to make tremendous progress on a number of tasks in machine learning, computer vision, and robotics. However, a principled understanding of the roots of this success – as well as why and to what extent deep learning works – still eludes us.
This course will aim to cover fundamental ideas and phenomena that underlie recent developments in deep learning. We will explore topics revolving around optimization landscape of neural network training; generalization of deep learning models; generative models such as generative adversarial networks (GANs) and variational autoencoders (VAEs); adversarial aspects of machine learning; interpretability, robustness and privacy of deep learning models; and (deep) reinforcement learning.
The course will be a mix of lectures and student presentations. Each presentation will involve surveying some of the recent advances in the field and providing a starting point for a subsequent class discussion on the merits and shortcomings of the presented state-of-the-art. Class projects will aim to address some of these identified shortcomings. The focus will be on building a principled understanding of deep learning via a mixture of empirical evaluations and theoretical modeling. The projects are intended to serve as a starting point for a subsequent publication in an ML conference.