The course is a basic introduction to machine learning, including:

• Supervised learning (PAC learning, VC dimension, perceptron, SVM, stochastic gradient descent, deep learning, boosting, decision trees)
• Unsupervised learning (principal component analysls, clustering, EM algorithm)

The course will include both theory and applied machine learning,
and a special emphasis will be put on machine learning algorithms.

See here for lecture notes from last year:

http://ml-intro-2016.wikidot.com/course-schedule

The excercises will be done in Python; The course has large parts that are mathematical in nature.