Admission requirements
Description
How can we use AI/ML techniques in real life? What kind of models have been used in different fields? In this course; we will introduce domain specific AI/ML applications and discuss challenges we are facing in using AI/ML in different fields. In addition; special datasets created and processed in diverse domains will be explained. This course will especially focus on fields including society; environment; health care and life science. Various types of data will be introduced such as biological imaging; spatial; or network data.
This course is a combination of lectures; practical sessions and project work. After the introductory lectures and practical sessions; students will design their own AI/ML applications.
Course objectives
Understand and discuss applications of the most used ML/AI models in the following fields o Time series o Spatial databases o Network datasets o Human mobility data o Text corpora o Healthcare data o Biological imaging
Apply and/or implement evaluation metrics to compare the performance of AI/ML models
Understand limitations and best practices of AI/ML models
Understand FAIR principles; ethics; algorithmic fairness; identify and discuss potential problems in different fields
Apply and compare different ML/AI models in a chosen topic
Schedule
Teaching method
Lectures
Practical sessions / working groups
Presentation of own work (including a written report following a template)
Assesment method
Grading is based on:
assignments completion (10%)
contribution to a project: presentation, report (90%) = final presentation (25%) + final report (65%)
The final grade is the weighted average of the above as indicated.
If an assignment or a presentation is not completed, the resulting grade is a 0. There will be no retakes for the assignments and the presentations. The final grade can only be sufficient if the weighted average grade is at least 5.5.
Resit, review & feedback
There will be no retakes for the assignments and the presentations. The retake for the final report is a one-time resubmission with an improved version. The final grade can only be sufficient if the weighted average grade is at least 5.5.
Reading list
Registration
Application period
For minor students; TU Delft; Erasmus and LDE students: Tuesday 19 May 13.00h until 30 June. Please use this link to enroll.
More information about the application procedure can be found on this website.
Contact
minordatascience@liacs.leidenuniv.nl