Fundamentals of Machine Learning and Generative AI
Niveau
Second cycle, master’s degree
Learning outcomes of the courses/module
The participants:
• can describe the fundamentals of machine learning and generative AI
• can identify tools (e.g., libraries, cloud platforms, or software tools) that can support machine learning
• can design simple machine learning projects
• can independently carry out simple machine learning projects
• can identify common GenAI tools
• can describe the fundamentals of machine learning and generative AI
• can identify tools (e.g., libraries, cloud platforms, or software tools) that can support machine learning
• can design simple machine learning projects
• can independently carry out simple machine learning projects
• can identify common GenAI tools
Prerequisites for the course
not applicable
Course content
Machine Learning Fundamentals
- Introduction to machine learning, learning paradigms, and the machine learning pipeline
- Classical machine learning methods, including regression, tree-based methods, ensemble methods, and clustering
- Fundamentals of neural networks and deep learning
- Model performance, evaluation, bias–variance tradeoff, and cross-validation
Generative AI
- Overview of generative models: large language models, generative adversarial networks, diffusion models, and variational autoencoders
- Transformer architecture and attention mechanisms
- Pretraining, fine-tuning, and instruction tuning
- Fundamentals of prompting and controllability
- Introduction to retrieval-augmented generation
- Image-based and multimodal generative models
- Introduction to machine learning, learning paradigms, and the machine learning pipeline
- Classical machine learning methods, including regression, tree-based methods, ensemble methods, and clustering
- Fundamentals of neural networks and deep learning
- Model performance, evaluation, bias–variance tradeoff, and cross-validation
Generative AI
- Overview of generative models: large language models, generative adversarial networks, diffusion models, and variational autoencoders
- Transformer architecture and attention mechanisms
- Pretraining, fine-tuning, and instruction tuning
- Fundamentals of prompting and controllability
- Introduction to retrieval-augmented generation
- Image-based and multimodal generative models
Recommended specialist literature
- Géron, A. (2022): Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow
- Tunstall, L., von Werra, L., Wolf, T. (2022): Natural Language Processing with Transformers
- Raschka, S. (2024): Build a Large Language Model
- James, G. (2023): An Introduction to Statistical Learning
- Tunstall, L., von Werra, L., Wolf, T. (2022): Natural Language Processing with Transformers
- Raschka, S. (2024): Build a Large Language Model
- James, G. (2023): An Introduction to Statistical Learning
Assessment methods and criteria
Portfolio exam
Language
English
Number of ECTS credits awarded
6
Semester hours per week
Planned teaching and learning method
Lecture, group work, presentation, and discussion of assignments
Semester/trimester in which the course/module is offered
1