Admission requirements
Assumed prior knowledge
It is assumed that the student has
Good programming skills in Python (see for example the content of the courses 'Programmeermethoden' and 'Algoritmiek')
Good knowledge about Data Science and Machine Learning techniques (see for example the content of the courses 'Data Science', 'Machine Learning' and 'Symbolic AI')
Familiarity with deep learning (see 'Introduction to Deep Learning'--could be followed in parallel)
Description
The fields of Data Science and Machine Learning deal with large volumes of data. Complex algorithms such as stochastic gradient descent, gradient boosting and support vector machines are able to model this data and make predictions about future trends. Most of these algorithms have a high number of hyperparameters, that need to be tuned correctly in order for the resulting model to perform well. Properly tuned hyperparameters can determine the difference between mediocre performance and state-of-the-art performance. When presented with a new dataset, common problems that need to be addressed are: Which algorithm to use and how to tune the hyperparameters to obtain good predictive performance. The research field of Automated Machine Learning (AutoML) focuses on how to automate this process.
Course objectives
There will be several lectures presented by the lecturers (approximately 6) in which core techniques from the field of AutoML are presented. The other lecture slots are filled with student presentations and discussions. Students will work in small teams (exact size to be determined), analyzing and understanding a seminal research paper and presenting it to the other students. Furthermore, the students will perform various research assignments to gain hands-on knowledge of state-of-the-art techniques in the field of AutoML. At the end of the course, the student should be able to:
Understand the various aspects of AutoML (e.g., search space, search algorithm, evaluation mechanism and the combination of these).
Understand the various problem definitions that are commonly solved by AutoML techniques
Analyze state-of-the-art hyperparameter optimization techniques, including (but not limited to) Bayesian optimization and hyperband.
Apply state-of-the-art AutoML tools on novel problem instances (e.g., using a convolutional neural networks or gradient boosting on a new image dataset)
Apply various meta-learning and transfer learning techniques (e.g., MAML, Reptile, matching networks, memory-augmented neural network).
Evaluate relevant AutoML papers.
See Bloom’s taxonomy for a further explanation of the required level of understanding per item.
Timetable
You will find the timetables for all courses and degree programmes of Leiden University in the tool MyTimetable (login). Any teaching activities that you have sucessfully registered for in MyStudyMap will automatically be displayed in MyTimeTable. Any timetables that you add manually, will be saved and automatically displayed the next time you sign in.
MyTimetable allows you to integrate your timetable with your calendar apps such as Outlook, Google Calendar, Apple Calendar and other calendar apps on your smartphone. Any timetable changes will be automatically synced with your calendar. If you wish, you can also receive an email notification of the change. You can turn notifications on in ‘Settings’ (after login).
For more information, watch the video or go the the 'help-page' in MyTimetable. Please note: Joint Degree students Leiden/Delft have to merge their two different timetables into one. This video explains how to do this.
Mode of instruction
Lectures (content will be provided by the lecturers)
Seminar (content will be provided through student presentations & discussions)
Research programming assignments
Exam
Course load
Total hours of study: 168 hrs. (= 6 EC)
The time will be divided between:
Preparing the lectures
- weekly: read the paper that will be presented
- once: prepare to present a paper
Attending the lectures
Research assignments
- programming / designing experiments / report writing
Exam (preparation + taking the exam)
Assessment method
The weighting of the final grade will be:
20% presentation
30% research assignments
50% final exam
The minimal grade per component is a 1.0. Each of the components needs to be completed with a passing grade (higher or equal to a 5.5), in order to successfully complete the course.
Reading list
Recent and seminal papers from the AutoML literature. For the exam, the open access book Metalearning: Applications to Automated Machine Learning and Data Mining will be used (this can be downloaded from the Springer website). Exact contents will be announced during class.
Registration
Every student has to register for courses with the enrollment tool MyStudyMap. There are two registration periods per year: registration for the fall semester opens in July and registration for the spring semester opens in December. Please see this page for more information.
Please note that it is compulsory to both preregister and confirm your participation for every exam and retake. Not being registered for a course means that you are not allowed to participate in the final exam of the course. Confirming your exam participation is possible until ten days before the exam.
Extensive FAQ's on MyStudymap can be found here.
Contact
Lecturers: dr. J.N. van Rijn
Remarks
More information will be available on the dedicated website for this course, hosted on BrightSpace.