Automated Machine Learning
From Alexandra Blank
Students and employees of Leiden University may upload videos on Kaltura. Only upload videos that you made or that you are authorized to use. You must own the copyright to your video or hold permissions from the copyright holders. If you believe your copyright-protected work was posted on Kaltura without authorization, you can send an e-mail message to: email@example.com or flag the video in question. Leiden University expressly disclaims all liability for damages in any way resulting from or in connection with the use of videos on Kaltura.
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.
Lecturers: Dr. J.N. van Rijn