Overview
Academic contacts
Offerings
Requisites
Other learning activities
Learning activities
Learning outcomes
Be able to demonstrate an in-depth theoretical and practical understanding of machine learning algorithms.
Be able to apply and evaluate machine learning solutions in real-life applications.
Demonstrate and articulate a critical understanding of the latest approaches, theories, and research activities in machine learning.
Be able to demonstrate knowledge of using the Python programming language and software environment for advanced data analysis and machine learning.
Assessments
Additional information
· General concepts of machine learning · Model evaluation and hyperparameter tuning · Machine learning classifiers · Ensemble learning · Unsupervised learning· Transfer learning and multitask learning · Health data analysis · Sentiment analysis · deep learning.
Each student is expected to spend on average three hours per teaching week reading the lecture notes, books chapters and other recommended materials relevant to the topic covered in that week and spend a similar amount of time working on the workshop exercises for that week.