skip to primary navigationskip to content
 

Dr David GT Barrett

Dr David GT  Barrett

Research Associate, University of Cambridge.

College Research Associate, St John's College, Cambridge

The goal of my research is to understand how neural networks learn to perform difficult computations, such as probabilistic inference in deep generative models. My approach is to combine techniques from machine learning, statistical physics and neuroscience.

Computational and Biological Learning,
Office BE-435,
Information Engineering Division,
Department of Engineering,
University of Cambridge


Cambridge CB2 1PZ

Biography:

I received an undergraduate degree in Theoretical Physics from Trinity College Dublin in 2006, and an M.Sc in Sparse Coding in 2007. I completed a Ph.D in Computational Neuroscience and Machine Learning at the Gatsby Unit, UCL, with Prof. Peter Latham and Prof.Prof. Peter Dayan in 2012. After my PhD, I held a joint-research position at the École Normale Supérieure, Paris and the Champalimaud Centre for the Unknown, Lisbon. In May 2014, I joined theComputational and Biological Learning Lab at Cambridge University, where I have been working with Máté Lengyel. I am also a College Research Associate at St John's College, Cambridge.

Departments and Institutes

Department of Engineering:

Research Interests

Neural Networks, Sparse coding, Variational Inference, The Helmholtz Machine, Auto-encoding, Optimal compensation theory, Quadratic Programming, Balanced network theory, Noise correlations, Visual cortex tuning, Natural sound processing and Information theory.