Module Description Lecture Slides
  1. Introduction
  2. General (Artificial) Neural Networks
  3. Multilayer Perceptrons (MLPs)
  4. Training of Multi-Layer Perceptrons
  5. Radial Basis Function Networks
  6. Learning Vector Quantization, Self-organizing Maps
  7. Hopfield Networks
  8. Recurrent Neural Networks
  9. Supervised Learning / Support Vector Machines
Exercises (german)
  1. Threshold Logic Units
  2. Network and Training of Threshold Logic Units
  3. Update Order, Funktion Approximation
  4. Method of smallest squares, Logic Regression
  5. Activity functions, Gradient Descent, Radial Basis Function Networks
  6. Radial Basis Function Networks, Function Approximation
  7. Radial Basis Function Networks
  8. Tournament lerning / Learning Vector Quantization, Self-organizing Maps
  9. Hopfield Networks
Exams