Additional Info

• ECTS credits: 6
• University: University of Hamburg
• Semester: 3
• Topics:

   

  1. Basics: analogy; layout of neural nets, universal approximation, NP-completeness
  2. Feedforward nets: backpropagation, variants of Stochastistic Gradients
  3. Deep Learning: problems and solution strategies
  4. Deep Belief Networks: energy based models, Contrastive Divergence
  5. CNN: idea, layout, FFT and Winograds algorithms, implementation details
  6. RNN: idea, dynamical systems, training, LSTM
  7. ResNN: idea, relation to neural ODEs
  8. Standard libraries: Tensorflow, Keras, PyTorch
  9. Recent trends
• Prerequisites:

   

  1. Skript
  2. Online-Werke:
     • http://neuralnetworksanddeeplearning.com/
     • https://www.deeplearningbook.org/