Jump to content

Yee Whye Teh

From Wikipedia, the free encyclopedia
Yee-Whye Teh
Alma materUniversity of Waterloo (BMath)
University of Toronto (PhD)
Known forHierarchical Dirichlet process
Deep belief networks
Scientific career
FieldsMachine learning
Artificial intelligence
Statistics
Computer science[1]
InstitutionsUniversity of Oxford
DeepMind
University College London
University of California, Berkeley
National University of Singapore[2]
ThesisBethe free energy and contrastive divergence approximations for undirected graphical models (2003)
Doctoral advisorGeoffrey Hinton[3]
Websitewww.stats.ox.ac.uk/~teh/ Edit this at Wikidata

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]

Education

[edit]

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

[edit]

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

[edit]

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]

References

[edit]
  1. ^ a b Yee Whye Teh publications indexed by Google Scholar Edit this at Wikidata
  2. ^ a b "Yee-Whye Teh, Professor of Statistical Machine Learning". stats.ox.ac.uk.
  3. ^ a b Yee Whye Teh at the Mathematics Genealogy Project Edit this at Wikidata
  4. ^ a b www.stats.ox.ac.uk/~teh/ Edit this at Wikidata
  5. ^ Gram-Hansen, Bradley (2021). Extending probabilistic programming systems and applying them to real-world simulators. ox.ac.uk (DPhil thesis). University of Oxford. OCLC 1263818188. EThOS uk.bl.ethos.833365.
  6. ^ Gasthaus, Jan Alexander (2020). Hierarchical Bayesian nonparametric models for power-law sequences. ucl.ac.uk (PhD thesis). University College London. OCLC 1197757196. EThOS uk.bl.ethos.807804. Free access icon
  7. ^ Yee Whye Teh at DBLP Bibliography Server Edit this at Wikidata
  8. ^ Whye Teh, Yee (2003). Bethe free energy and contrastive divergence approximations for undirected graphical models. utoronto.ca (PhD thesis). University of Toronto. hdl:1807/122253. OCLC 56683361. ProQuest 305242430.
  9. ^ Geoffrey E. Hinton; Simon Osindero; Yee-Whye Teh (1 July 2006). "A fast learning algorithm for deep belief nets". Neural Computation. 18 (7): 1527–1554. doi:10.1162/NECO.2006.18.7.1527. ISSN 0899-7667. PMID 16764513. Zbl 1106.68094. Wikidata Q33996665.
  10. ^ Yee W. Teh; Michael I. Jordan; Matthew J. Beal; David M. Blei (2005). "Sharing Clusters among Related Groups: Hierarchical Dirichlet Processes" (PDF). Advances in Neural Information Processing Systems 17. Advances in Neural Information Processing Systems. Wikidata Q77688418.
  11. ^ "On Bayesian Deep Learning and Deep Bayesian Learning". nips.cc.