Lecturer: Benjamin Paassen
Fields: Machine Learning
Content
AI systems such as image generators, language models, automatic decision making systems, and much more are widely known. But what are the underlying models and algorithms that make these systems work? How does one take data as input and automatically extract models from them? This is the subject of machine learning.
The course will provide an introduction to machine learning. The core knowledge and skills taught by the course are:
– the basic recipe behind machine learning (training data, model architecture, loss function, training/optimization, and inference)
– the fundamental mathematical concepts behind machine learning
– example models and algorithms, from classic machine learning to neural networks
– types of machine learning (supervised, unsupervised, reinforcement)
– core notions for responsible machine learning, namely: interpretable models, adversarial examples, and fairness
In more detail, the course will have four sessions with the following topics:
1. Basic Concepts: Functions, learning algorithms, optimization, linear regression (as an example of a learning algorithm), regularization, probability theory, machine learning theory, how to design a ML experiment, how to read an ML paper
2. Recipes for interpretable and robust machine learning: Distance-based models, adversarial examples, and decision trees
3. Artificial neural networks and deep learning: Neural network modules, recipes for neural networks, generative models (diffusion and large language models)
4. Reinforcement learning and ethics
Each session is accompanied by a (voluntary) programming exercise in Python. Exercise sheets (and slides) can be found here: https://bpaassen.gitlab.io/Teaching.html
Literature
- Literature is optional and more regarded as ‘further/complementary reading’:
- Barber, D. (2012). Bayesian Reasoning and Machine Learning. Cambridge University Press. Cambridge, UK. http://www.cs.ucl.ac.uk/staff/d.barber/brml/
- Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning. MIT Press. Cambridge, MA, USA. https://www.deeplearningbook.org/
- Paaßen, B., Artelt, A., Hammer, B. (2019). Lecture Notes on Applied Optimization. Bielefeld University. https://pub.uni-bielefeld.de/record/2935200
- Shalev-Shwartz, S., and Ben-David, S. (2014). Understanding Machine Learning: From Theory to Algorithms. Cambride University Press. Cambridge, UK. https://www.cs.huji.ac.il/w~shais/UnderstandingMachineLearning/
- Barocas, S., Hardt, M., and Narayanan, A. (2023). Fairness and Machine Learning. MIT Press. Cambridga, MA, USA. https://fairmlbook.org/
Lecturer
Benjamin Paaßen is Junior Professor for Knowledge Representation and Machine Learning at Bielefeld University and research affiliate at the Educational Technology Lab of the German Research Center for Artificial Intelligence (DFKI). Their research foci are interpretable machine learning, machine learning for education, and limitations of large language models (especially as research tools).
Affiliation: Bielefeld University
Homepage: https://bpaassen.gitlab.io/