BEV033DLE – Deep Learning

Quick links: Schedule | Forum | BRUTE

The course introduces deep neural networks and deep learning – a branch of machine learning and artificial intelligence. It aims at providing the relevant algorithmic and theoretical concepts needed for successfully designing and training NNs. At the same time it strives at providing technical and practical skills in this domain.

This course is best suited for bachelor students in their last year and for master students. We expect students to have basic knowledge in machine learning and AI. This short introductory video should help you to decide whether this course is interesting and suitable for you.

• 18.05.2022 The exam terms are scheduled for 31.05.2022, 09:45 - 11:15 and 21.06.2022, 11:30 - 13:00, both in KN:E-301 as well as online
• 23.03.2022 Survey for EuroTeQ courses link
• 20.02.2022 Lecture recordings can be found in this playlist
• 16.02.2022 Online / hybrid meetings are managed as conference rooms in BRUTE. Login and select the tab “conference rooms” for the course BEV033DLE - Deep Learning. You should see the list of all planned rooms The meetings are associated to parallels (either 102 or 103) but you may attend the one that is suitable for you. The meeting platform is BigBlueButton (BBB). All BBB recordings will appear in the same list, they are published automatically, a few hours after the meeting. You might prefer to watch recordings via the BBB internal viewer instead of using the mp4 link, because in the former you can choose between the presentation or the blackboard in full screen mode.

• 15.02.2022 Lecture live streaming: follow this link

• Teachers: Boris Flach, Alexander Shekhovtsov and Jan Šochman
• Prerequisites:
  • Fundamentals of mathematics comparable to the following courses: Linear Algebra (B0B01LAG), Calculus (B0B01MA2), Optimization (B0B33OPT) as well as Probability, Statistics, and Theory of Information (B0B01PST ).
  • Besides proficient knowledge of mathematics as given above, students are expected to have solid knowledge in the following areas of computer science and artificial intelligence: basics of graph theory and related algorithms; basics of pattern recognition, empirical risk minimisation, linear classifiers, support vector machines as in Pattern Recognition and Machine Learning (B4B33RPZ or BE4B33RPZ).

• Course format: (2/2)
  • lectures: weekly
  • alternating practical and theoretical labs (tutorials): weekly
• Schedule: Summer semester 2022
  • Lectures: Wed, 11:00-12:30, KN:E-301 (+ online streaming)
  • Labs/Seminars: Thu, 9:15-10:45 in KN:E-128 and 11:00-12:30 in KN:E-112. Fri, 11:00-12:30 online

• Grading/Credits:
  • Thresholds for passing: at least 50% of the regular points in the labs and at least 50% of the regular points in the exam
  • Weights for final grading: 50% practical labs + 50% written exam = 100% (+ bonus points)
  • Credits: 6 CP

• Textbooks and References:
  • I. Goodfellow, Y. Bengio and A. Courville, Deep Learning, MIT Press, 2016

• Lectures
• Labs and Seminars