Programme info

Micro-credential: Machine Learning of Natural Language Processing

  • Study load: 12 ECTS credits
  • Language of instruction: English
  • ​Maximum number of participants: 5
  • Location: Stadscampus​
  • Faculty: Faculty of Arts

This micro-credential consists of two modules.

Machine Learning provides a comprehensive introduction to machine learning, covering key concepts such as supervised, unsupervised and reinforcement learning, regression, classification and clustering. It explores a range of machine learning methods, including logistic regression, k-nearest neighbours, decision trees, random forests, Naive Bayes and support vector machines, with practical applications using tools such as scikit-learn. The course then moves into neural networks and deep learning, introducing multilayer networks, optimization techniques and practical work with PyTorch. Finally, advanced topics such as convolutional neural networks, recurrent networks, language models, sequence-to-sequence learning and attention are covered, with the exact topics adapting to available time and developments in the field.

Building on the foundations of Machine Learning, the course introduces the core concepts and techniques of Natural Language Processing, with a particular focus on modern transformer-based models. Students explore language modelling, word embeddings and key NLP applications such as sentiment analysis, author profiling, chatbots and the extraction of semantic, syntactic and discourse-level information. The course combines theoretical insights with hands-on experience using widely adopted tools such as spaCy, NLTK and Hugging Face Transformers, while also considering the ethical and societal implications of NLP. The course concludes with a collaborative project in which students apply their knowledge to a real-world text classification problem.

Practical organisation

The micro-credential is a combination of lectures, practice sessions, guest lectures and project work.

Learning outcomes

This micro-credential focuses on the following learning outcomes.

1. The participant will have theoretical knowledge about the history and the main frameworks of Machine Learning.

2. The participant will have theoretical knowledge of the main machine learning algorithms and paradigms and will study some of them in depth.

3. The participant will be able to develop machine learning pipelines and set up their own machine learning experiments using Python modules.

4. The participant will have theoretical and practical knowledge of machine learning using neural networks.

5. The participant will understand the fundamental problems and approaches in automatic Natural Language Processing and know its history as a subfield within Linguistics and Artificial Intelligence.

6. The participant will have insight into the basic algorithms developed within NLP for morphological, syntactic, semantic, and discourse processing.

7. The participant will acquire hands-on experience with software for text categorization, language understanding, translation, and generation.

Evaluation

  • All courses extensively rely on weekly, hands-on homework assignments, ensuring the acquisition of new, practical insights on a regular basis. The homework takes the form of engaging assignments on real-world datasets that challenge the students to apply the theoretical concept introduced during the interactive class sessions.
  • The final evaluation of all three courses depends on project work, the goal and finality of which can be determined by the individual students, in close correspondence with the course teachers.
  • An attractive feature of the evaluation of the NLP course (in the 2nd semester) is that students will participate in an ongoing shared task in the field.

Other courses on this topic

You might also be interested in these courses.

Looking for a course in a completely different subject area? Take a look at the range of courses on www.nova-academy.be.