Recent & Upcoming Talks

When DNNs are trained on ground-truth information, they can reach or exceed human performance in many visual tasks. However, no …

Unsupervised deep learning provides a framework for understanding how brains learn rich scene representations without ground-truth …

Presenting new results from two projects using unsupervised deep neural networks to learn about image structure from static or moving …

We suggest that characteristic errors in gloss perception may result from the way we learn vision more generally, through unsupervised …

How do we see the outside world? Materials with complex appearances, like a glossy bumpy surface seen under natural lighting, pose …

News

Dec-01-19

Awarded Humboldt Research Fellowship

Alexander von Humboldt Foundation

I was recently awarded a Humboldt Research Fellowship for Postdoctoral Researchers, from the Alexander von Humboldt Foundation: https://www.humboldt-foundation.de/web/home.html. I will take up the 2-year fellowship in late 2019, to continue my work with Prof. Roland Fleming at the Justus Liebig University in Giessen, Germany, on unsupervised deep learning of visual properties.
Sep-01-19

New paper published: Learning to See Stuff

Current Opinion in Behavioral Science

My first paper with Roland Fleming is out now, in which we present a case for the importance of unsupervised learning in core visual perception: https://doi.org/10.1016/j.cobeha.2019.07.004.
Aug-12-19 – Aug-14-19

Symposium: How Humans and Machines Learn to See

Rauischholzhausen Castle, Hesse, Germany

Together with Prof Roland Fleming, I am organising a 3-day symposium this August, bringing together machine learning researchers, computational visual neuroscientists, and developmental vision scientists to discuss ecologically plausible visual learning at the Rauischholzhausen Castle, Hesse, Germany. Funded by the German Research Council (DFG) under the SFB project ‘Cardinal Mechanisms of Perception’ http://www.allpsych.uni-giessen.de/sfb/index_de.html

Experience

 
 
 
 
 
January 2018 – Present
Giessen, Germany

Postdoc

Justus-Liebig University

  • Psychophysics
  • Unsupervised deep learning
 
 
 
 
 
July 2017 – December 2017
London, UK

Data Scientist

Twitter

Optimising measurement of perceived video quality.
 
 
 
 
 
February 2015 – June 2017
Cambridge, UK

Postdoc

MRC Cognition and Brain Sciences Unit, University of Cambridge

  • Representational similarity analysis
  • fMRI
  • Deep learning
 
 
 
 
 
July 2014 – October 2013
London, UK

Teaching Fellow in Visual Perception

University College London

Coordinating and lecturing undergraduate psychology courses.
 
 
 
 
 
November 2011 – February 2015
Brisbane, Australia

PhD candidate

University of Queensland

Thesis: “Norms are Not the Norm: Testing Theories of Sensory Encoding using Visual Aftereffects”

Contact