BEV033DLE – Deep Learning

Overview

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.

News

  • 24.03.2020 The deadline for the first home work has been extended by two weeks because of the suspension of teaching.
  • 19.03.2020 Dear Students, we are going to resume teaching in distant mode next week. We have decided to use the BigBlueButton platform for it, which is now integrated in Brute. You will receive an e-mail with an invitation link shortly before the meeting next Wednesday, 11:00. You may have a look at this youtube video, which shows how BBB will work for you as a student. The sessions will be recorded and available for offline download/watching. We will use the same platform for the labs and seminars. We are considering the option to join the lab parallels into one session. Please use this Doodle poll, to indicate the time slots suitable for you. Mark both of them if you have no restrictions. Our plan for next week is: lecture 4 (backprop) and lab 2. The materials are online.
  • 11.03.2020 Dear Students, the next lecture (lecture 4. on back-propagation) and the 2. lab will be delayed by two weeks due to teaching suspension. We publish the materials for your convenience. It might happen that after the “corona break” teaching will be resumed in distant mode. Sasha is currently testing variants for this. We will provide more information as soon as we know more.

Details

  • 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
    • Lectures: Wed, 11:00-12:30, KN:E-126
    • Labs/Seminars: Thu, 9:15-10:45 and 11:00-12:30, both in KN:E-128
  • 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: 40% practical labs + 60% written exam = 100% (+ bonus points)
    • Credits: 6 CP
  • Textbooks and References:
    • I. Goodfellow, Y. Bengio and A. Courville, Deep Learning, MIT Press, 2016

Materials

courses/bev033dle/start.txt · Last modified: 2020/03/24 15:04 by flachbor