 |
| Detailed information |
| Original study plan |
Bachelor's programme Computer Science 2025W |
| Learning Outcomes |
Competences |
| Students are able to independently select and adapt machine learning methods for real-world problems. They can evaluate the advantages and disadvantages of these methods and critically reflect on their performance in different application areas. They are able to make informed decisions about the use of methods. Furthermore, they are able to independently implement and adapt machine learning methods using common program libraries and integrate them into practical applications, as well as optimize models and analyze performance using suitable metrics.
|
|
| Skills |
Knowledge |
Students
- understand the fundamental concepts and principles of machine learning, such as the differences between supervised, unsupervised, and reinforcement learning, as well as typical areas of application (k2).
- possess in-depth knowledge of basic machine learning algorithms such as Linear Regression, k-Means, Nearest Neighbor, and Principal Component Analysis (PCA), including their mathematical foundations and areas of application (k4).
- are familiar with various metrics for evaluating machine learning models, such as confusion matrices, precision, recall, F1-score, and ROC curves, and understand their importance for model quality (k3).
- know advanced machine learning techniques such as Support Vector Machines (SVM) and Random Forests, including their theoretical foundations and application examples (k4).
- have a foundational understanding of neural networks and deep learning, including the operation of simple neural networks and the use of deep learning frameworks like TensorFlow or Keras (k2).
- are familiar with common machine learning libraries such as Scikit-learn and TensorFlow, and understand their structure and functionality for implementing machine learning models (k3).
- know the advantages and disadvantages of various machine learning techniques and their use in real-world scenarios, including performance analysis and application limitations (k5).
|
- Principles of Machine Learning: Students understand the fundamental concepts and principles of machine learning, such as the differences between supervised, unsupervised, and reinforcement learning, as well as typical areas of application.
- Machine Learning Methods: Students possess basic knowledge of machine learning methods such as Linear Regression, k-Means, Nearest Neighbor, and Principal Component Analysis (PCA), including their mathematical foundations and areas of application.
- Metrics for Evaluating Machine Learning Models: Students are familiar with various metrics for evaluating machine learning models, such as confusion matrices, precision, recall, F1-score, and ROC curves, and understand their importance for model quality.
- Advanced Machine Learning Methods: Students have knowledge of advanced machine learning techniques such as Support Vector Machines (SVM) and Random Forests, including their theoretical foundations and application examples.
- Fundamentals of Neural Networks and Deep Learning: Students have a foundational understanding of neural networks and deep learning, including the implementation and training of simple neural networks and the use of deep learning frameworks like TensorFlow or Keras.
- Machine Learning Libraries: Students are familiar with common machine learning libraries such as Scikit-learn and TensorFlow, and understand their structure and functionality for implementing machine learning methods.
- Application Areas and Performance of Machine Learning Methods: Students have knowledge of the advantages and disadvantages of various machine learning methods and their use in real-world scenarios, including performance analysis and application limitations.
|
|
| Criteria for evaluation |
Written exam
|
| Methods |
Slide presentations complemented by online demos and examples presented on the blackboard.
The lecture is also supported by a MOOC, providing videos, compact scripts, and exercises.
|
| Language |
English and French |
| Study material |
Electronic course material is made available for download
|
| Changing subject? |
No |
| Corresponding lecture |
(*)INBIPVOBIIN: VO Bioinformatics (3 ECTS)
|
|
