Machine learning studies automatic methods for learning to make accurate predictions, to understand patterns in observed features and to make useful decisions based on past observations.
This course introduces theoretical machine learning, including mathematical models of machine learning, and the design and rigorous analysis of learning algorithms.
Here is a tentative list of topics. (Bullets do not correspond precisely to lectures.)
- PAC learning basics, and PAC learning in Neural Networks
- Boosting and unsupervised boosting
- Graphical model basics
- Spectral methods: a case study of consistent algorithms
- Reinforcement learning
Minimum grade of A- in CMSC422 (or equivalent) or CMSC498M; permission of CMNS-Computer Science department and instructor.
- Basic machine learning concepts
* Supervised/unsupervised/reinforcement learning
* Classification, Regression, Cross validation, Overfitting, Generalization
* Deep neural networks
- Basic calculus and linear algebra
* Compute (by hand) gradients of multivariate functions
* Conceptualize dot products and matrix multiplications as projections
* Solve multivariate equations using, etc, matrix inversion, etc
* Understand basic matrix factorization
- Basic optimization
* Use techniques of Lagrange multipliers for constrained optimization problems
* Understand and be able to use convexity
- Basic probability and statistics
* Understand: random variables, expectations and variance
* Use chain rule, marginalization rule and Bayes' rule
* Make use of conditional independence, and understand "explaining away"
* Compute maximum likelihood solutions for Bernoulli and Gaussian distributions
Lecture scribing (40%)
Office hours: TBA