HY587
Neural Networks and Learning of Hierarchical Representations

Computer Science Department
University of Crete

Announcement

The course lectures will take place online via Zoom (the schedule is Tuesday, Thursday at 18:00- 20:00). The students who wish to attend the lectures will have to subscribe to the course mailing list (hy587-list@csd.uoc.gr). An email will be sent (at the day of the lecture) that will contain the Zoom link for joining the online lecture.

General Information

Course Description: The scientific activity of the last decade revealed many new directions and highly successful extensions of Neural Networks towards learning data representations for various perception systems. Representations of this kind are composed of many layers of nonlinear calculations (multilayer architectures) and are based on classic artificial neural networks. In recent years it has become evident that learning such multilayered representations can contribute to a significant improvement in perception systems performance. The purpose of this course is to present an introduction to artificial neural networks and in learning hierarchical representations based on those network structures. The course will focus on architectures, methodologies and algorithms, and will also include laboratory exercises.

Course Instructor: Nikos Komodakis