Module Handbook

  • Dynamischer Default-Fachbereich geändert auf INF

Course INF-75-71-K-7

Advanced Topics in Machine Learning (Seminar) (2S, 4.0 LP)

Course Type

SWS Type Course Form CP (Effort) Presence-Time / Self-Study
- K 4.0 CP 92 h
2 S Seminar 28 h
(2S) 4.0 CP 28 h 92 h

Basedata

SWS 2S
CP, Effort 4.0 CP = 120 h
Position of the semester 1 Sem. in WiSe/SuSe
Level [7] Master (Advanced)
Language [EN] English
Lecturers
Area of study [INF-KI] Intelligent Systems
Livecycle-State [NORM] Active

Possible Study achievement

  • Verification of study performance: presentation
  • Examination number (Study achievement): 67573 ("Deep Learning (Seminar)")
  • Details of the examination (type, duration, criteria) will be announced at the beginning of the course.

Contents

Topics are flexible and according to student interests. They may include:
  • Overfitting, regularization, and early stopping
  • Stochastic Optimization
  • Generative approaches (e.g., GANs, Universum Learning)
  • Deep Bayesian learning
  • Sophisticated architectures
  • Piecewise-linear deep networks
  • Globally optimal training of polynomial networks

Literature

  • Goodfellow, Ian, Yoshua Bengio, and Aaron Courville.  Deep learning . MIT Press, 2016.
  • Schmidhuber, Jürgen. "Deep learning in neural networks: An overview."  Neural networks  61 (2015): 85-117.
  • Selected research articles

Requirements for attendance (informal)

None

Requirements for attendance (formal)

None

References to Course [INF-75-71-K-7]

Module Name Context
[INF-75-71-M-7] Advanced Topics in Machine Learning (Seminar) P: Obligatory 2S, 4.0 LP
Course-Pool Name
[INF-KI_S-KPOOL-7] Seminars of the teaching area Intelligent Systems