Teaching

Neurocomputing

Level: Master.

Responsability: lectures and exercises.

Course website: https://www.tu-chemnitz.de/informatik/KI/edu/neurocomputing

Materials: https://julien-vitay.net/course-neurocomputing/

Syllabus

  1. Linear algorithms
    1. Optimization
    2. Linear regression
    3. Linear classification
    4. Learning theory
  2. Neural networks
    1. Multi-layer perceptron
    2. Modern neural networks
  3. Computer Vision
    1. Convolutional neural networks
    2. Object detection
    3. Semantic segmentation
  4. Generative modeling
    1. Autoencoders
    2. Restricted Boltzmann machines
    3. Generative adversarial networks
  5. Recurrent neural networks
    1. Recurrent neural networks, LSTM
    2. Natural Language Processing
    3. Attentional neural networks
  6. Self-supervised learning
    1. Transformers
    2. Contrastive learning

Deep Reinforcement Learning

Level: Master.

Responsability: lectures and exercises.

Course website: https://www.tu-chemnitz.de/informatik/KI/edu/deeplrl

Materials: https://julien-vitay.net/course-deeprl/

Syllabus

  1. Tabular RL
    1. Bandits
    2. Markov Decision Processes
    3. Dynamic Programming
    4. Monte Carlo control
    5. Temporal Difference
    6. Function approximation
    7. Deep learning
  2. Model-free RL
    1. Deep Q-network
    2. Beyond DQN
    3. Policy Gradient
    4. A2C / A3C
    5. DDPG
    6. TRPO / PPO
    7. SAC
  3. Model-based RL
    1. Model-based RL
    2. Learned models
    3. AlphaGo
    4. Successor representations

Introduction to AI

Level: Bachelor.

Responsability: exercises.

Course website: https://www.tu-chemnitz.de/informatik/KI/edu/ki

Syllabus

  1. Blind search
  2. Heuristic search
  3. Game theory
  4. Constraint propagation
  5. Optimization
  6. Neural networks
  7. Support vector machines
  8. Probability theory
  9. Information theory
  10. Decision trees
  11. Estimators
  12. Reinforcement learning