Machine Learning Systems

Photo of Baback Moghaddam

Dr. Baback Moghaddam

Mail Stop 306-463
4800 Oak Grove Drive
Pasadena, CA 91109

Office: 306-456
Phone: (818) 354-2395
FAX: (818) 393-6141
Email:
Education: Ph.D., Massachusetts Institute of Technology, 1996
Interests: Bayesian Statistics, Machine Learning, Computer Vision, Sparse Optimization
Bibliography: Citeseer, Google Scholar, Libra, DBLP, CSB [External Links]

Biography : Baback Moghaddam joined Caltech/JPL in 2007 as a Principal Scientist, and is member of the Machine Learning and Instrument Autonomy Group. Prior to that he was a Senior Research Scientist at the Mitsubishi Electric Research Laboratory (MERL) in Cambridge Massachusetts since 1997. He received his Ph.D. from the Electrical Engineering and Computer Science (EECS) department of the Massachusetts Institute of Technology in 1996, where he was also a Research Assistant and member of the Vision & Modeling Group of the MIT Media Laboratory since 1992. As part of his doctoral dissertation at MIT he developed an automatic face recognition system which won the 1996 DARPA "FERET" Face Recognition Challenge. During his 10 years as a Research Scientist at MERL he authored numerous papers on 2D face recognition and 3D facial modeling in leading journals and conferences (including the core chapter in Springer-Verlag's Biometric Series: The Handbook of Face Recognition). He was also the recipient of the 2001 Pierre Devijver Prize from the International Association of Pattern Recognition for his innovative work on Bayesian Face Recognition. Dr. Moghaddam has over 75 publications and 15 patents in the areas of computer vision, statistical modeling, pattern recognition and machine learning.
Some Recent Publications:

Paper Icon
Djorgovski et al., Towards Automated Classification of Transient Events in Synoptic Sky Surveys,
NASA Conference on Intelligent Data Understanding, (CIDU'11), Mountain View, CA, October 19-21, 2011.
Download PDF (CL #11-4519)
Paper Icon
Kitching et al., Gravitational Lensing Accuracy Testing 2010 (GREAT10) Challenge Handbook
Annals of Applied Statistics, Vol. 5, No. 3, IMS Press, 2011.
Download PDF (CL #11-3768)
Paper Icon
Baback Moghaddam, Benjamin Marlin, Emtiyaz Khan and Kevin Murphy,
Accelerating Bayesian Structural Inference for Non-Decomposable Gaussian Graphical Models.
Advances in Neural Information Processing Systems (NIPS 22), MIT Press, 2009.
Download PDF (CL #09-4528)
Paper Icon
Max Bajracharya, Baback Moghaddam, Andrew Howard, Shane Brennan and Larry H. Matthies,
A Fast Stereo-based System for Detecting and Tracking Pedestrians from a Moving Vehicle.
International Journal of Robotics Research, Vol. 28, No. 8, July, 2009.
Download PDF (CL #09-2063)
Paper Icon
Bridle et al., Handbook for GREAT08 Challenge: An Image Analysis Competition for Cosmological Lensing.
Annals of Applied Statistics, Vol. 3, No. 1, pp. 6-37, IMS Press, 2009.
Download PDF (CL #08-4723)
Paper Icon
Mahabal et al., Toward Real-Time Classification of Astronomical Transients.,
Classification and Discovery in Large Astronomical Surveys, edited by C. A. L. Bailer-Jones,
American Institute of Physics, pp. 287-293, AIP Press, 2008.
Download PDF [External Link]
Paper Icon
Baback Moghaddam, Amit Gruber, Yair Weiss and Shai Avidan.
Sparse Regression as a Sparse Eigenvalue Problem.
Information Theory & Applications Workshop (ITA'08), January 2008.
Download PDF (CL #08-4561)
Paper Icon
Baback Moghaddam, Yair Weiss and Shai Avidan.
Fast Pixel/Part Selection with Sparse Eigenvectors.
Proc. of the 11th IEEE International Conference on Computer Vision (ICCV'07), October 2007.
Download PDF (CL #07-2491)
Paper Icon
Baback Moghaddam, Yair Weiss and Shai Avidan.
Generalized Spectral Bounds for Sparse LDA.
Proc.of the 23rd International Conference on Machine Learning (ICML'06), June 2006.
Download PDF [External Link]
Paper Icon
Baback Moghaddam, Yair Weiss and Shai Avidan.
Spectral Bounds for Sparse PCA: Exact and Greedy Algorithms.
Advances in Neural Information Processing Systems (NIPS 18), MIT Press, 2006.
Download PDF [External Link]