Statistical Machine Learning
Learning Objective:The students will (a) learn the theory and key algorithms used in machine learning (b) Get hands-on machine learning experience by implementing several algorithms, applying them to datasets and analyzing their performance (c) Understand how to apply machine learning methods to new problems relevant to their application domains, by completing a project.
Machine learning offers a new paradigm of computing-- computer systems that can learn to perform tasks by finding patterns in data, rather than by running code specifically written to accomplish the task by a human programmer. The most common machine learning scenario requires a human teacher to annotate data (identify relevant phenomenon that occurs in the data), and use a machine learning algorithm to generalize from these examples. Generalization is at the heart of machine learning-- how can the machine go beyond the provided set of examples and make predictions about new data. In this class we will look into several machine learning paradigms and specific learning algorithms, analyze their performance and learn the theory behind them.
Topics Covered:Artificial Intelligence, machine learning, statistics, probability, optimization. Supervised learning, unsupervised learning. Decision Trees, margin-based learning, statistical learning, graphical models.
Prerequisites:A bachelor degree in computer science or an equivalent field. Students not in the Computer Science master's program should seek department permission to register. Familiarity with linear algebra, statistics, probability and algorithm design is assumed.
Applied / Theory:
Homework:Students will have to complete homework assignments once every two weeks. Some homework assignment will require the students to implement machine learning algorithms.
Projects:Students will have to complete a final project. The project can be completed by individual students or small groups. Students will be expected to identify a decision problem, collect data, formulate it as a machine learning problem and match it with an appropriate machine learning method. Students will have to submit a proposal and a final report.
Exams:Final and a mid-term exam.
Textbooks:Official textbook information is now listed in the Schedule of Classes. NOTE: Textbook information is subject to be changed at any time at the discretion of the faculty member. If you have questions or concerns please contact the academic department.
Tentative: OPTIONAL TEXTBOOKS:
1. Tom M. Mitchell, Machine Learning (1st edition), McGraw-Hill. ISBN: 9780070428072. Notes: Recommended.
2. Christopher Bishop, Pattern Recognition and Machine Learning (Information Science and Statistics), Springer. ISBN: 9780387310732. Notes: Recommended.