Machine Learning Core Courses
The core courses for our machine learning graduate programs consists of six courses, divided into the set core and menu core courses, as outlined below.
These four required core courses together provide a foundation in machine learning, statistics, probability and algorithms:
- 10-701: Introduction to Machine Learning or 10-715: Advanced Introduction to Machine Learning*
- 10-716: Advanced Machine Learning — Theory and Methods
- 36-700: Probability and Mathematical Statistics or 36-705: Intermediate Statistics*
- 10-718: Machine Learning in Practice
*Note: Master's students may take 10-701: Introduction to Machine Learning and 36-700: Probability and Mathematical Statistics. Ph.D. students must take 10-715: Advanced Introduction to Machine Learning and 36-705: Intermediate Statistics.
Student must also take two of the menu core courses, listed below:
- 10-703: Deep Reinforcement Learning or 10-707: Topics in Deep Learning
- 10-708: Probabilistic Graphical Models
- 10-725: Optimization for Machine Learning (formerly Convex Optimization)
- 10-734: Foundations of Autonomous Decision Making Under Uncertainty
- 15-750: Algorithms in the Real World or 15-850 Advanced Algorithms
- 15-780: Graduate Artificial Intelligence
- 10-805: Machine Learning With Large Datasets
- 36-707: Regression Analysis
- 36-709: Advanced Statistical Theory I
- 36-710: Advanced Statistical Theory II
Note: The two menu core courses must be taken from separate lines in the list above. For example, a student may not use both 15-750: Algorithms in the Real World and 15-850: Advanced Algorithms to satisfy their menu core requirements. Menu core courses may also be used as electives.