No.224 Seminar ： Loss function perspective of machine learning: What does a machine learn?
- Assistant Professor Han BAO (Hakubi 12th batch, Graduate School of Science)
- 2022/09/20 4:30pm
- Zoom and onsite at the Hakubi Center for Advanced Research
- English
- Hybrid manner ／ Closed (only availble for members affiliatted to Kyoto University)
Summary
Machine learning has become so complicated that it often lacks a clear perspective to understand what a system indeed learns. In today’s talk, I would like to briefly introduce machine learning from the viewpoint of loss functions and optimization, which has a fundamental connection to how one should evaluate a system. The central question in the talk is, “Does our system capture what we want to elicit?” Through our recent studies on robust machine learning and self-supervised learning, I show some examples of what a system does and does not learn, which will be an important step towards reliable knowledge induction.