Yee-Whye Teh is a professor of statistical machine learning in the Department of Statistics at the University of Oxford.^[3] Prior to 2012, he was a reader at the Gatsby Charitable Foundation computational neuroscience unit at University College London.^[1] His institutional affiliations also include DeepMind, the University of California, Berkeley, and the National University of Singapore.

Teh attended Dunman High School, earned a BMath from the University of Waterloo, and received his PhD from the University of Toronto. Supervised by Geoffrey Hinton, he completed his 2003 doctoral thesis titled "Bethe free energy and contrastive divergence approximations for undirected graphical models" (handle: https://hdl.handle.net/1807/122253).

His work is primarily in machine learning, artificial intelligence, statistics, and computer science.^[4,1] His notable areas of research include the Hierarchical Dirichlet process and Deep belief networks.

Teh was born in Bukit Mertajam, Malaysia in 1977. He received his secondary education at Dunman High School, graduating in 1994. Teh then received his tertiary education at the University of Waterloo and the University of Toronto, where he was awarded a PhD in 2003 for research supervised by Geoffrey Hinton.^[6]

Teh was a postdoctoral fellow at the University of California, Berkeley and the National University of Singapore before joining University College London as a lecturer.^[1,5] He was one of the original developers of deep belief networks and hierarchical Dirichlet processes.^[1] He has also served as a research scientist at Google DeepMind.

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.^[7] He served as program co-chair of the International Conference on Machine Learning (ICML) in 2017, one of the premier conferences in machine learning.