Hi, I am Sebastian and I am a Ph.D. candidate in Computer Science at Harvard SEAS. During my graduate studies, I want to build intelligent team members to support human teams in complex tasks. The domain I am focusing on is health care, where it is crucial to design models that are intelligible and not black boxes. Unfortunately, most recent advances in machine learning, specifically deep learning, are black boxes which makes it hard to explain their predictions and classifications. I want to change that and make it possible to use these powerful tools for tasks such as automated chart abstraction or patient phenotyping. Therefore, my research agenda comprises the following points:
- Build interactive tools to evaluate complex deep learning models.
- Improve existing models for healthcare by utilizing deep learning methods from natural language processing.
- Combine the two points to have models that are intelligent team members that can explain their recommendations.
- Take over the world.
My academic advisor is Barbara Grosz. I am also working with the Harvard NLP Group, supervised by Sasha Rush, and the Intelligent Interactive Systems Group. For more information about my past, you can have a look at my CV (last updated Oct '16).
Feel free to contact me with requests for discussions, questions about my research or whatever you feel the need of talking to me about. My email-address is my_last_name (at) seas.harvard.edu or you can follow me on twitter @S_Gehrmann.