The talk starts at 12:15.

Please note that due to COVID-19, the participants can watch the streamed talk on Teams with a link (below).

Speaker: Håvard Kvamme

Location: Teams: Click here to join the meeting

Title: Time-to-Event Prediction with Neural Networks

Abstract:

In the last decades the analytical value of data has really become apparent and the amount of data collected has vastly increased. This enables us to approach problems in more data driven manners. In this talk, I'll present some of the research I've been a part of during my PhD studies, where we combined recent developments in machine learning with statistical methods for time-to-event prediction, all in an effort to better answer the question: “When in the future will a given event occur?”. Mainly, this considers how neural networks can be applied for this purpose. However, we studied both which statistical methods that were best suited to be extended with neural networks, and how to evaluate the performance of such methods.