Instructor: Andreas Aristidou

Type: Postgraduate (Elective)

Prerequisite: Knowledge of a high-level programing language, and experience in programming with Python. Experience with linear algebra, calculus, statistics, and probability.

Lectures: Monday, 15:00-18:00 (ΘΕΕ01 #147)

Recitations: Monday, 14:00-15:00 (ΘΕΕ01 #147)

Laboratory: Wednesday, 15:00-16:30 (ΘΕΕ01 #101)

Teaching Assistants: Yiangos Georgiou and Theodoros Kyriakou

Overview

This course will offer an introduction to machine learning algorithms, the use of deep learning and its applications in computer vision and graphics. The course will also operate as a graduate-level seminar with weekly readings (1 hour per week), summarizations, and discussions of recent papers.
You can download the syllabus of the course here...

News

Sign-up now to Moodle using code handed out in class!

Course Schedule and Lectures

1. Introduction to Deep Learning in Graphics and Computer Vision Course Objectives and Syllabus.
   [PDF in EN | 12.80 MB]
2. Image Classification Introduction to image classification, supervised/unsupervised methods, linear classifiers.
   [PDF in EN | 18.40 MB]
3. Image Classification Regulazation, Optimization, and Backpropagation.
   [PDF in EN | 26.4 MB]

Lab Schedule

Sign-up now to Moodle using code handed out in class!

Assignments

All Assignments will be announced in Moodle. Sign-up using the code handed out in class!

Text Book and Bibliography

• Deep Learning, Ian Goodfellow, Yoshua Bengio, Aaron Courville, MIT Press, 2016.
• Computer Vision: Advanced Techniques & Applications, Steve Holden, Clanrye International, 2019.
• Pattern Recognition and Machine Learning , by Christopher Bishop, Springer, 2016.
• Cheat Sheets for Machine Learning.
• Cheat Sheets for Artificial Intelligence. Follow this link.