6.883 Meta Learning


Graduate Level
Units: 3-0-9
Prerequisites: 6.036 or 6.867
Instructor:  Dr. Iddo Drori,  idrori@mit.edu
Schedule: TR4-5:30, online instruction
Enrollment limited to 50.
This subject counts as an Aritificial Intelligence concentration subject. Traditionally, humans develop new machine learning algorithms and learn topics by reading, watching videos, and taking courses. Meta learning or learning to learn, has allowed machines to learn to learn new algorithms; discover physics formulas or symbolic expressions that match data; develop systems for automatic model discovery; teach machines to read, learn and reason; ace science exams at the high school level; and solve the SAT. In this graduate level course students develop components of a program that participates in an undergraduate course as an AI. The course covers advanced deep learning topics used for  learning to learn, including: automated machine learning, meta-learning, deep learning on graphs, transformers, knowledge graphs, symbolic regression, program induction, Bayesian learning, and deep reinforcement learning. The highlight of the course is participating in building a system that passes 6.036 Introduction to Machine Learning as a virtual student: teaching a machine how to learn machine learning. The system will solve very specialized tasks: learning 6.036 from course material: notes, exercises, exams, solutions, labs, etc., and will participate in 6.036 by solving exercises, quizzes, labs, exams, and ultimately pass the course as a virtual online student, or 6.036AI.
More information on how this subject will be taught can be found at