Skip to content

Machine Learning Beyond Static Datasets – ESSAI 2023

European Summer School on AI Course

Abstract: Machine learning studies the design of models and training algorithms in order to learn how to solve tasks from data. Whereas historically machine learning has concentrated primarily on static predefined training datasets and respective test scenarios, recent advances also take into account the fact that the world is constantly evolving. In this course, we will go beyond the train-validate-test phase and explore modern approaches to machines that can learn continually. In addition to a comprehensive overview of the breath of factors to consider in such continual learning, the course will outline the basics of techniques that span mitigation of forgetting across multiple tasks, selection of new data in ongoing training, and robustness with respect to unexpected data inputs.

Materials

The European Summer School on AI – ESSAI 2023 has streamed and recorded the five lectures and has made them freely available online on videolectures.net for anyone to view: http://videolectures.net/ESSAIandACAI2023_mundt_machine_learning/

The below links also provide the presented slides for the respective topics of the individual lectures:

Day 1: The Present – Static Datasets & Re-use. Download Slides
Day 2: The Past – Forgetting & Memory. Download Slides
Day 3: From Past to Future – Memory & Growth. Download Slides
Day 4: The Future – Data Selection & Learning Curricula. Download Slides
Day 5: The Unknown – Open World Learning & Evaluation. Download Slides