Lectures
Zoom link to lectures: (log into courses to see link)
(lectures are held every week on Monday at 10:15)
Lecture 01 - Sep 7 - Course organisation (PDF, mp4) + Supervised learning (part I) (PDF, mp4)
Lecture 02 - Sep 14 - Supervised learning (part II) (PDF, mp4) + Kahoot
Lecture 03 - Sep 21 - Unsupervised learning (part I) (PDF, mp4)
Lecture 04 - Sep 28 - Unsupervised learning (part II) (PDF, mp4) + Kahoot
Lecture 05 - Oct 5 - Deep learning (part I) (PDF, mp4)
Lecture 06 - Oct 12 - Deep learning (part II) (PDF, mp4) + Kahoot
Lecture 07 - Oct 19 - Regularisation methods (part I) (PDF, mp4)
Lecture 08 - Oct 26 - Regularisation methods (part II) (PDF, mp4) + Kahoot
Lecture 09 - Nov 2 - Ensemble learning (part I) (PDF, mp4)
Lecture 10 - Nov 9 - Ensemble learning (part II) (PDF, mp4) + Kahoot
Lecture 11 - Nov 16 - Intermediate project presentations (check the order of presentations here)
Lecture 12 - Nov 23 - Performance metrics (part I) (PDF, mp4)
Lecture 13 - Nov 30 - Performance metrics (part II) (PDF, mp4) + Kahoot
Lecture 14 - Dec 7 - Guest lecture (no practice sessions this week)
Lecture 14.01: What can we do with natural language processing? (Behrad Moeini) (Colab, mp4)
So far, students in the machine learning course learned a few concepts. There is a field going on-demand is using machine learning to understand human languages. In the presentation, we want to explain some python codes to those who want to know about NLP's basics.
Lecture 14.02: ICML2020: Some insight on the top-notch ML research, the good, the bad, and the ugly. (Novin Shahroudi) (PDF, mp4)
We are going to have a look at some of the highlights of the ICML2020 including the major topics, the influential papers, the ones awarded, and the ones that made a fuss.