Lecture: Deep Learning for Visual Recognition


  • Lecturer(s):
  • Start: 05.11.2020
  • Dates: Thu. 10:15 - 11:45 (Online)
  • Course number: MA-INF 2313
  • Curriculum: Master
  • Effort: 6 CP
  • Exams: 19th February, 16:00, and 29th March, 13:00


  • Tutor(s):
  • Start: TBD
  • Dates: TBD


Neural networks are making a comeback!  Deep learning has taken over the machine learning community by storm, with success both in research and commercially.  Deep learning is applicable over a range of fields such as computer vision, speech recognition, natural language processing, robotics, etc.  This course will introduce the fundamentals of neural networks and then progress to state-of-the-art convolutional and recurrent neural networks as well as their use in applications for visual recognition.  Students will get a chance to learn how to implement and train their own network for visual recognition tasks such as object recognition, image segmentation and caption generation.

No formal pre-requisites.  Students should already be comfortable with concepts in probability theory and optimization and are recommended to have taken at least one course in machine learning or computer vision.  Exercises will be a mix of theory and practical (Python).

Additional Documents


Assignment Sheets

Exercise 0: Setup
Assignment sheet  (PDF document, 67 KB)
Exercise 1: MLBasics
Assignment sheet  (PDF document, 186 KB)
Exercise 2: NeuralNetworks
Assignment sheet  (PDF document, 158 KB)
Exercise 3: Optimization and Regularization
Assignment sheet  (PDF document, 161 KB)
Exercise 4: Advanced Optimization and Initialization
Assignment sheet  (PDF document, 165 KB)
Exercise 5: Normalization and Regularization
Assignment sheet  (PDF document, 195 KB)
Exercise 6: CNNs
Assignment sheet  (PDF document, 146 KB)
Exercise 7: ResNet
Assignment sheet  (PDF document, 168 KB)
Exercise 8: AEs-GANs-RNNs (non-mandatory sheet)
Assignment sheet  (PDF document, 227 KB)