Fall 2017

Princeton University

A thorough introduction to machine learning principles such as online learning, decision making, gradient-based learning, and empirical risk minimization. It also explores regression, classification, dimensionality reduction, ensemble methods, neural networks, and deep learning. The course material is self-contained and based on freely available resources.

The course provides an introduction to machine learning.

**Topic covered**:

- Online learning and decision making
- Learning from examples and generalization
- Empirical risk minimization and regularization
- Introduction to convex analysis
- Gradient-based learning
- Implementation and analysis of learning algorithms for regression, binary classification, multiclass categorization, and ranking problems
- Dimensionality reduction methods
- Ensemble methods and boosting
- Neural networks and deep learning
- Markov decision precesses

No data.

No data.

**NOTICE:** All material of the course is self-contained and based on freely available books and surveys.

Main references:

- Understanding Machine Learning: From Theory to Algorithms, by Shai Shalev-Shwartz and Shai Ben-David
- Online convex optimization, by Elad Hazan
- Machine Learning, by Tom Mitchell
- An Introduction to Computational Learning Theory, by Michael Kearns & Umesh Vazirani
- Machine Learning: A Probabilistic Perspective, by Kevin Murphy,

Further advanced references: - Convex Optimization, by Stephen Boyd and Lieven Vandenberghe

- Convex optimization: algorithms and complexity, by Sebastien Bubeck
- Artificial Intelligence: A Modern Approach, by Stuart Russell and Peter Norvig

Python Tutorials - An interactive python tutorial from LearnPython.com

- Tutorial for Python 2.7 from python.org
- Tutorial for Python 3 from python.org

Lecture slides available at Shcedule

No videos available

Assignments and midterm available at Assignments

Percepts available at Shcedule