University of Cambridge > > CCIMI Seminars > Deep reinforced active learning

Deep reinforced active learning

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Paula Smith.

In this talk I will give an overview of my research at GSK .ai. I introduce a paper in the field of active learning and the application of deep reinforcement learning to image classification in the active learning domain. In this work we aimed to solve several major biases or oversights which exist in the literature in active learning, a machine learning technique widely used in many industrial applications. The paper I will present provides initial solutions to the aforementioned issues in the field, applied to medical imaging datasets. My group members are now developing the technique for much wider-spread applications across the domain of deep learning in drug discovery.

This talk is part of the CCIMI Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2024, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity