Machine Learning: Theory and Applications
The broad goal of Machine Learning is to design automatic methods for extracting information from data. It constitutes the basis for Artificial Intelligence and is successfully applied in many fields ranging from biology and medicine to finance, economy, image and signal processing, information theory, meteorology, etc. The goal of this short course is to provide a gentle introduction to some fundamental topics of machine learning. The three equally important aspects of Machine Learning, probabilistic-theoretical, algorithmic and empirical will be presented with various applications. The prerequisites for the course are a basic course in probability theory and a course in linear algebra. It will be also assumed that the students have some background in programming.
The following will be covered during the lectures:
• Lecture 1 (Unsupervised Learning)
• Lecture 2 (Theoretical foundations of Supervised Learning)
• Lecture 3 (Algorithms of supervised learning)
• Lecture 4 (Supervised learning and convexification)
Arnak Dalalyan has got his Bachelor’s degree in Mathematics from Yerevan State University in 1997. He continued his studies in University of Maine, France where he did PhD in Statistics in 2001. Currently Mr. Dalalyan is a Professor of Statistics and Machine Learning in ENSAE, France.
Organizer: College of Science & Engineering
Venue: 413W, PAB