Basic Information
Online Learning# Definition, Basic Examples, Perceptron, Littlestone Dimension. Pac Learning# Definition, Loss Functions, Erm Principle, Vc Dimension, Boosting. Metric Properties of Vc Classes. Uniform Convergence. Sample Compression Schemes, Examples, and Pac Learnability. Universal Learning.__ Learning Outcomes At The End of The Course The Students Will Know# 1. Learn The Basic Ideas in Statistical Learning Theory. 2. Understand The Importance of Definitions and Be Able to Change The According to Applications.____ 3. Know Guiding Algorithmic Principles, Like Compression and Boosting 4. Be Familiar With Bridges Between Learning Theory and Other Areas Of Math, Like Metric Spaces and Probability Theory._
Faculty: Mathematics
|Undergraduate Studies
|Graduate Studies
Pre-required courses
(94412 - Probability (advanced) and 104032 - Calculus 2m and 104166 - Algebra Am) or (104013 - Differential and Integral Calculus 2t and 104016 - Algebra 1/extended and 104034 - Introduction to Probability H) or (104066 - Algebra A and 104222 - Probability Theory and 104281 - Infinitesimal Calculus 2)