Machine Learning refers to a set of methods designed to extract information from data with the goal to make predictions or perform various types of decisions.
This area has witnessed a remarkable growth during the last decade as machine learning is central to the development of intelligent systems and the analysis of massive and complex data found in science or social media. Machine learning algorithms currently enable systems such as Siri, the Google self driving car, or PathAI for medical diagnostics.
This course is an introduction to the theoretical foundations of machine learning and will be focused on the underlying mathematical concepts
needed to understand the methods used in modern data science, without neglecting the algorithmic and computational aspects of the subject.
Topics of the course include Support Vector Machines, Reproducing Kernel Hilbert Spaces, the Vapnik-Chervonenkis theory,
concentration inequalities, dimensionality reduction and spectral clustering.
This is class is targeted to graduate students interested in mastering theoretical tools underlying machine learning and data science. Even though algorithmic aspects of the topics will not be ignored, this course will not duplicate existing courses on machine learning or data science offered in
the Computer Science Department that are focused on algorithmic implementation and computation.
Prerequisite
Students attending this course are expected to have a solid background in linear algebra, undergraduate real analysis (MATH 4331-4332) and basic probability.
Student evaluation is based on two assignments: (i) scribing class notes and (ii) final project.
(i) Scribing class notes: for every lecture, a student will be in charge of scribing class notes and producing a well-polished latex document;
each scribe will be assited by another student acting as reviewer/editor. The Latex document will be prepared using the macro in the attached
Example Latex file. Each student will scribe 2 lectures.
(ii) The final project will be based on the critical reading of one (or possibly more than one) research paper. I recommend to form a team of 2 students for this project.
The topic of the final project need to be relevant to the class and need to receive my prior approval. Students need to form a team and submit a proposal of their project
by FRI March 6. My detailed instructions for the proposal and final project are given here.
Delivery of the final project and brief in-class presentataion are tentatively scheduled on WED May 6, 11am-2pm. Presentation instructions, list and calendar are here.
I will select or adapt a significant part of lectire material from:
Support Vector Machines, by Ingo Steinwart and Andreas Christmann, Springer 2008;
Learning Theory: An Approximation Theory Viewpoint by F Cucker and D. Zhou, Cambrigde 2007;
Learning with Kernels, by B Schlkopf and A. Smola, The MIT Pres 2001
Notes and reference papers will be provided by the instructor.