Lecture materials for the Pattern Analysis and Machine Intelligence Praktikum at Goethe University.
The course material is divided into corresponding week subdirectories. Each notebook has a link to open in Google's Colab at the top. You don't need any local installation, simply click on a notebook and click the link at the top to open it in your browser.
The structure of the notebooks is inspired by popular online courses (like Andrew Ng's fantastic coursera classes) in such that they have blank lines and functions that need be filled in in order for the code to work.
If you have been unable to attend the lecture in person, the recommended order to go through the material each week is the following:
- Read the slides
- Go through any additional references or linked material
- Complete the notebook
Solution notebooks will be uploaded with a time delay. It is highly recommended that you attempt to complete the notebook yourself before taking a look at the solutions.
- Week 1: 15.04 – Intro Jupyter & Colab notebooks, Python review, version-control & documentation
- 22.04 – Easter holiday
- Week 2: 29.04* – Regression and gradient descent (Kaggle Titanic dataset)
- Week 3: 06.05 – Random forests (Sklearn intro & San Francisco Crime Challenge)
- Week 4: 13.05 – Intro to unsupervised learning (K-means or PCA)
- Week 5: 20.05 – Basic neural networks (Multi-layer perceptron on FashionMNIST)
- Week 6: 27.05 – Convolutional neural networks & frameworks (PyTorch, Revisiting FashionMNIST)
- Week 7: 03.06* – Unsupervised NNs (autoencoders, image generation - variational autoencoders)
- 10.06 – Pfingsten
- Week 8: 17.06 – Intro to basic reinforcement learning (Cart-pole)
- Week 9: 24.06 – Reinforcement learning: Q-Learning and QNN (some game)
- Week 10: 01.07 – Neural sequence models (Recurrent neural networks, text classification)
- Week 11: 08.07 – Neural sequence models (long-short-term memory, poetry generation)
- Week 12: 15.07 – State of the art outlook, project pitches and discussion (3 slide pitches)