Teaching

Machine Learning

The course covers various fields of machine learning, including supervised learning, unsupervised learning and reinforcement learning. See the course’s page : http://www.tu-chemnitz.de/informatik/KI/edu/ml

  1. Supervised Learning

    1. Optimization, linear classification and regression
    2. Learning theory
    3. Multi-layer perceptron
    4. Support vector machines
    5. Convolutional Neural Networks
    6. Generative networks
    7. Recurrent neural networks
  2. Reinforcement Learning

    1. Formal definition of the RL problem
    2. Dynamic Programming, Monte-Carlo, Temporal Difference
    3. Eligibility Traces, Function approximation
    4. Deep Reinforcement Learning

Computer Vision

The course covers different computer vision techniques, from simple image processing to top-down segmentation and feature matching. See the course’s page : http://www.tu-chemnitz.de/informatik/KI/edu/biver

  1. Image formation (geometric primitives, color spaces, compression)
  2. Image processing (histogram equalization, linear filtering, Fourier transforms, pyramids and wavelets)
  3. Geometric transformations (parametric transformations, mesh-based warping, face swapping, morphing)
  4. Feature detection and matching (feature detectors and descriptors, feature tracking, line detection)
  5. Segmentation (active contours, split and merge, mean shift and mode finding, Graph cuts)
  6. Motion, optical flow (translational alignment, optical flow, layered motion)