I’m a machine learning researcher at Qualcomm and finishing my PhD in Machine Learning at the University of Amsterdam where I work with Max Welling. I received a Bachelors degree in Computer Science from Utrecht University and a Masters in Artificial Intelligence from the University of Amsterdam (both cum laude). I’m a cofounder of Scyfer (acquired by Qualcomm in 2017). I received the 2017 Google PhD Fellowship. Here is my CV.
My research is focussed on data-efficient deep learning and supervised and unsupervised learning of invariant and equivariant visual representations. I’m also interested in the theoretical foundations of representation learning and deep learning, which I’m trying to understand using tools from group representation theory.
T.S. Cohen, M. Geiger, Jonas Koehler, Max Welling, Convolutional Networks for Spherical Signals. In Principled Approaches to Deep Learning Workshop ICML 2017.
T. Matiisen, A. Oliver, T.S. Cohen, J. Schulman, Teacher-Student Curriculum Learning. ArXiv preprint 1707.00183, 2017
T.S. Cohen, M. Welling, Steerable CNNs. International Conference on Learning Representations (ICLR), 2017
L.M. Zintgraf, T.S. Cohen, T. Adel, M. Welling, Visualizing Deep Neural Network Decisions: Prediction Difference Analysis. International Conference on Learning Representations (ICLR), 2017
T. Adel, T.S. Cohen, M. Caan, M. Welling, 3D Scattering Transforms for Disease Classification in Neuroimaging. Neuroimage: clinical, 2017 (accepted)
L.M. Zintgraf, T.S. Cohen, M. Welling, A New Method to Visualize Deep Neural Networks. ArXiv preprint 1603.02518, 2016
T.S. Cohen, M. Welling, Transformation Properties of Learned Visual Representations. International Conference on Learning Representations (ICLR), 2015.
T.S. Cohen, Learning Transformation Groups and their Invariants. Master’s thesis, University of Amsterdam, 2013. (1st place University of Amsterdam thesis prize 2014)