Robert Pinsler

Robert Pinsler

PhD Student in Machine Learning

University of Cambridge

I am a final-year PhD student at the Machine Learning Group of the University of Cambridge, supervised by Prof. Carl E. Rasmussen and advised by Dr. José Miguel Hernández-Lobato. My research focuses on data-efficient learning under uncertainty, including work on reinforcement learning, active learning and Bayesian deep learning. I am also interested in applying machine learning to problems in science and engineering.

My work revolves around two common themes:

  1. Reasoning about uncertainty: I believe that obtaining accurate uncertainty estimates is crucial for efficient data acquisition and exploration. Therefore, I use the language of probability and Bayesian inference to express and reason about uncertainty.
  2. Exploiting prior knowledge: Efficient learning requires to equip models with the right inductive biases. In particular, I am interested in exploiting prior knowledge about the symmetries of the underlying problem, such as translation- or rotation-equivariance.
Interests
  • Reinforcement Learning
  • Active Learning
  • Bayesian Deep Learning
  • AI for Science
  • Robotics
Education
  • PhD in Machine Learning, est. 2021/2022

    University of Cambridge

  • MSc in Computer Science, 2017

    TU Darmstadt

  • BSc in Business Informatics, 2014

    DHBW Mannheim

Recent Publications

Experience

 
 
 
 
 
Research Intern
Jun 2020 – Sep 2020 Berlin, Germany
Data-efficient meta-learning
 
 
 
 
 
Research Assistant
Sep 2016 – Feb 2017 Darmstadt, Germany
Simultaneous estimation of foreground and background intensities for motion deblurring
 
 
 
 
 
Research Assistant
Oct 2015 – Dec 2015 Darmstadt, Germany
Deep learning for robotic grasping
 
 
 
 
 
Student Intern
Oct 2014 – Sep 2015 Walldorf, Germany
Data analysis, machine failure prediction and evaluation of large-scale sensor data