Samuel A. Barnett

Samuel A. Barnett

PhD Candidate in Computer Science

Princeton University

Biography

I am a PhD candidate at Princeton University in Computer Science, where I work within the fields of machine learning and cognitive science. I am advised primarily by Ryan P. Adams in the Laboratory for Intelligent Probabilistic Systems and secondarily by Thomas L. Griffiths in the Computational Cognitive Science Lab. Previously, I was the Daniel M. Sachs Scholar at Princeton.

I am interested in questions that arise from the interaction between AI systems and the humans that implement them: how can we design systems that are adaptable to the needs of different users? How can we model human social inference and interaction, and how might our understanding shape the systems we design? How should AI researchers and engineers reason about the ethical implications of their work?

Previously, I received an MMathPhil in Mathematics and Philosophy from the University of Oxford. My Mathematics dissertation focussed on the theoretical convergence properties of generative adversarial networks (GANs), and was supervised by Varun Kanade. My Philosophy thesis focussed on (philosophical) decision theories for AI systems, and was supervised by Hilary Greaves.

Interests

  • Artificial Intelligence
  • Cognitive Science
  • Philosophy and Ethics of AI

Education

  • Daniel M. Sachs Scholar at Princeton, 2019

    Princeton University

  • MMathPhil in Mathematics and Philosophy, 2018

    University of Oxford

Contact