Yee Whye Teh

Yee-Whye Teh is a professor of statistical machine learning in the Department of Statistics, University of Oxford.^[4][5] Prior to 2012 he was a reader at the Gatsby Charitable Foundation computational neuroscience unit at University College London.^[6] His work is primarily in machine learning, artificial intelligence, statistics and computer science.^[1][7]

Yee-Whye Teh
Alma mater	University of Waterloo (BMath) University of Toronto (PhD)
Known for	Hierarchical Dirichlet process Deep belief networks
Scientific career
Fields	Machine learning Artificial intelligence Statistics Computer science[1]
Institutions	University of Oxford DeepMind University College London University of California, Berkeley National University of Singapore[2]
Thesis	Bethe free energy and contrastive divergence approximations for undirected graphical models (2003)
Doctoral advisor	Geoffrey Hinton[3]
Website	www.stats.ox.ac.uk/~teh/

Education

Teh was educated at the University of Waterloo and the University of Toronto where he was awarded a PhD in 2003 for research supervised by Geoffrey Hinton.^[3][8]

Research and career

Teh was a postdoctoral fellow at the University of California, Berkeley and the National University of Singapore before he joined University College London as a lecturer.^[2]

Teh was one of the original developers of deep belief networks^[9] and of hierarchical Dirichlet processes.^[10]

Awards and honours

Teh was a keynote speaker at Uncertainty in Artificial Intelligence (UAI) 2019, and was invited to give the Breiman lecture at the Conference on Neural Information Processing Systems (NeurIPS) 2017.^[11] He served as program co-chair of the International Conference on Machine Learning (ICML) in 2017, one of the premier conferences in machine learning.^[4]