Neural Networks (LTAT.02.001)
Important: The first lecture is on 13.02.2024. Please note that during first two weeks there will be no practice sessions. Check the tab Timetable for a detailed schedule.
The course presents the main concepts of the theory and practice of modern neural networks. It also gives students the basic understanding and tools to be able to independently apply neural networks to real problems.
The lectures are based on the book "Deep Learning" by Ian Goodfellow and Yoshua Bengio and Aaron Courville. In practices we are following the excellent Stanford university course "Convolutional Neural Networks for Visual Recognition" by Andrej Karpathy, Justin Johnson and Fei-Fei Li.
Tuesdays 14:15 room 1019
No Practices for the first two weeks!
Group 1: Wednesdays 10:15 room 2048
Group 2: Thursdays 12:15 room 1022
We will be using Campuswire for communication between students and instructors, questions, etc. If you are registered to the course, you will receive an invitation link to it. In the case that for some reason you don't, please contact one of the teaching assistants (contacts are in this page) or use this link to join the forum.
- Practice test 1 will give 30% of the final grade.
- Practice test 2 will give 30% of the final grade.
- A project will give 40% of the final grade.
- Homeworks and participation in the practice sessions will give up to 10% of the final grade in bonus (extra) points. Details are to be determined and will be explained in the practice session.
To pass the course you are required to at least get 50% of EACH component (exams and project). Attendance is not a factor in your grade, however, your presence during practice sessions allows us to assist and guide you with the material and assignments, plus we will reward students with bonus points.
and teaching assistants: