David McAllester
homepage:http://ttic.uchicago.edu/~dmcallester/
search externally:   Google Scholar,   Springer,   CiteSeer,   Microsoft Academic Search,   Scirus ,   DBlife

Description

Professor McAllester received his B.S., M.S., and Ph.D. degrees from the Massachusetts Institute of Technology in 1978, 1979, and 1987 respectively. He served on the faculty of Cornell University for the academic year of 1987-1988 and served on the faculty of MIT from 1988 to 1995. He was a member of technical staff at AT&T Labs-Research from 1995 to 2002. He has been a fellow of the American Association of Artificial Intelligence (AAAI) since 1997. Since 2002 he has been Chief Academic Officer at the Toyota Technological Institute at Chicago (TTIC).

Professor McAllester's research areas include machine learning, the theory of programming languages, automated reasoning, AI planning, computer game playing (computer chess), computational linguistics and computer vision. A 1991 paper on AI planning proved to be one of the most influential papers of the decade in that area. A 1993 paper on computer game algorithms influenced the design of the algorithms used in the Deep Blue system that defeated Gary Kasparov. A 1998 paper on machine learning theory introduced PAC-Bayesian theorems which combine Bayesian and nonBayesian methods. A 2001 paper with Andrew Appel introduced the influential step indexed model of recursive types in programming languages. He was part of a team (with Pedro Felzenszwalb, Ross Girshick and Deva Ramanan) that developed the deformable part model (DPM) which has become the community baseline system for object detection in computer vision. He is currently working with Raquel Urtasun and Koichiro Yamaguchi on stereo vision and optical flow algorithms with applications to robotic cars. He recently introduced a theoretical analysis of droupout learning for deep neural networks based on a PAC-Bayesian generalization bounds. He also recently posted an arxiv manuscript on a type-theoretic foundation for mathematics.


Lectures:

lecture
flag Unsupervised Learning for Stereo Vision
as author at  Machine Learning Summer School (MLSS), Chicago 2009,
6129 views
  debate
flag Lunch debate 23.5.2005
as coauthor at  Machine Learning Summer School (MLSS), Chicago 2005,
together with: Sanjoy Dasgupta (coauthor), Yann LeCun (coauthor), John Langford (coauthor), Yasemin Altun (coauthor), Zoubin Ghahramani (coauthor), Partha Niyogi (coauthor),
6857 views
debate
flag Lunch debate 25.5.2005
as coauthor at  Machine Learning Summer School (MLSS), Chicago 2005,
together with: Robert Schapire (coauthor), Yann LeCun (coauthor), John Langford (coauthor), Yasemin Altun (coauthor), Yoram Singer (coauthor),
5453 views
  lecture
flag Remembering Partha Niyogi
as author at  24th Annual Conference on Neural Information Processing Systems (NIPS), Vancouver 2010,
3785 views
lecture
flag Generalization Bounds and Consistency for Latent Structural Probit and Ramp Loss
as author at  25th Annual Conference on Neural Information Processing Systems (NIPS), Granada 2011,
3426 views
  invited talk
flag Some PAC-Bayesian Theorems
as author at  PASCAL Foundations and New Trends of PAC Bayesian Learning, London 2010,
3860 views
lecture
flag Training Structured Predictors for Novel Loss Functions
as author at  Large Scale Graphical Models,
3453 views
  lecture
flag Welcome
as author at  Machine Learning Summer School (MLSS), Chicago 2005,
together with: John Langford (coauthor),
4101 views
lecture
flag Learning on Structured Data
as author at  Machine Learning Summer School (MLSS), Chicago 2005,
3942 views
  lecture
flag A PAC-Bayesian Analysis of Dropouts
as author at  NIPS Workshops, Lake Tahoe 2013,
2085 views