PhD student position in Machine Learning for Surgical Performance Assessment (100%) in Zürich

ETH Zurich is one of the world’s leading universities specialising in science and technology. It is renowned for its excellent education, its cutting-edge fundamental research and its efforts to put new knowledge and innovations directly into practice.

The position will be part of a collaboration with a manufacturer of surgical training simulators. The overall aim of the project is to develop and use machine learning techniques for providing these simulators with automatic performance assessment and feedback functions in order to enhance their effectiveness as educational instruments.
Being able to give automatic performance assessment and feedback depend on the availability of adequate machine-level representations of expert knowledge. Our general approach is to model surgical procedures as sequential decision making tasks, and to learn such representations of expert knowledge from the behavioral characteristics of data generated by simulator users. One aspect we are particularly interested is to develop automatic teaching methods that can adaptively provide trainees with demonstrations of optimal behavior.

Within the project, there will be opportunities to work in the following directions: Surgical Performance Assessment, Surgical Activity Recognition, Inverse Reinforcement Learning, Machine Teaching, Representation Learning, Generative Modelling.