Faculty : Faculty of Engineering and Applied Sciences

School : Computer Science and Engineering

Course Description :

The course focuses on the state of the art statistical machine learning approaches. These include general energy-based models, and in particular restricted Boltzmann machines and auto encoders which are the foundational elements of deep neural networks. Bayesian inference and variational approximation. Mixture models. Basics of Monte Carlo methods. Statistical extensions of decision trees including bagging, boosting, and random forests. Model for time series analysis are considered including hidden Markov models and linear dynamical systems. The student should have a rather strong background in probability theory and statistical methods.

Faculty : Faculty of Engineering and Applied Sciences

School : Computer Science and Engineering

Course Description :

Students participate in Project-Based Learning activities in new advanced topics in Computer Systems, suggested by one or more faculty staff members.

Faculty : Faculty of Engineering and Applied Sciences

School : Computer Science and Engineering

Course Description :

Students participate in Project-Based Learning activities in new advanced topics in Computer Systems, suggested by one or more faculty staff members.

Faculty : Faculty of Engineering and Applied Sciences

School : Computer Science and Engineering

Course Description :

Series of research seminars conducted by Ph.D. students and based on self-learning and presentations of new advanced topics in Computer Systems selected by professors specialized in those topics. The student's evaluation is based on his understanding of the presented topics and presentations skills.

Faculty : Faculty of Engineering and Applied Sciences

School : Computer Science and Engineering

Course Description :

No Courses Description