Lecture
Nightingale Colloquium presents Veronika Cheplygina
- Date
- Tuesday 11 June 2019
- Time
- Explanation
- The seminar is targeted at a broad audience, in particular we invite PhD candidates and supervisors involved in the Data Science Research programme as well as colleagues from LIACS and MI to attend. The seminar is organized by the DSO, MI and LIACS.
- Location
- Snellius
Niels Bohrweg 1
2333 CA Leiden - Room
- 402
Not-so-supervised learning of algorithms and academics
Machine learning (ML) has vast potential in medical image analysis, improving early diagnosis of disease. However, ML needs large amounts of representative, annotated examples, which can be especially time-consuming and expensive for medical images. In the first part of my talk I will discuss several approaches to overcome this problem, including multiple instance learning, transfer learning and crowdsourcing, and give an overview of my own work on these topics. In the second part of the talk I will tell a bit more about my own path through these topics, and through academia in general. In a spirit similar to my "How I Fail" series, I hope to be able to offer some (possibly unconventional) advice for any subset of {early career, first generation, insecure} researchers.