From Equivariance to Naturality

Taco Cohen is a machine learning research scientist at Meta / FAIR. He received a PhD in machine learning from the University of Amsterdam advised by prof. Max Welling, where he developed the first equivariant deep networks. He was a co-founder of Scyfer, a company focussed on active deep learning, acquired by Qualcomm in 2017. At Qualcomm he led the generative models and data compression team. His current research is focussed on RL for code generation. He has done internships at Google Deepmind (working with Geoff Hinton) and OpenAI. He received the 2014 University of Amsterdam thesis prize, a Google PhD Fellowship, ICLR 2018 best paper award for “Spherical CNNs”, the Schouhamer-Immink prize for his PhD thesis, and was named one of 35 innovators under 35 in Europe by MIT in 2018.