Lecture Content:

Remarkable progress has been made in the field of artificial intelligence (AI) in recent years. Machine learning (ML), a subdiscipline of AI, attempts to develop techniques that enable computers to learn from data. The goal of ML methods is to reliably identify the underlying model for specific tasks.

The Practical Machine Learning (PML) lecture covers the theoretical foundations, basic concepts, and techniques of machine learning with a focus on problem-solving and practical applications. Students will have the opportunity to explore various ML algorithms and their applications in areas such as computer vision, natural language processing, and data mining. Throughout the course, you will work on various application tasks and a group project, applying the concepts you have learned to real-world datasets. You will learn to use common ML libraries and tools such as Scikit-Learn, TensorFlow, and Keras, and apply them to real-world datasets. You will also learn how to evaluate your models' performance and interpret their results.

The lecture style blends theory and practical applications with a focus on problem solving and hands-on experimentation. The theoretical portion of the course will be offered as a block at the beginning of the semester (early to mid-April). Afterwards, students will work on a machine learning research question individually or in small groups throughout the semester and present their findings in a scientific paper. A peer-review process ensures the quality of the papers, allowing students to benefit from mutual feedback on both the subject matter and the content.

This module covers the fundamentals and concepts of machine learning. Topics include:

• Introduction to Machine Learning and Its Applications
• Data preprocessing and feature engineering techniques.
• Supervised and unsupervised learning algorithms;
• Deep learning techniques such as convolutional and recurrent neural networks.
• Transfer learning and Tiny ML.
• Probabilistic machine learning.
• Evaluation metrics for ML models
• Hyperparameter tuning and model selection techniques.
• Interpretation of ML model results.

... Other interesting topics.

Information about the examination:

Performance is assessed by submitting project work and giving a 30-minute presentation on it.