Computer Science Department
Department of Electrical Engineering (by courtesy)
Stanford University
Room 156, Gates Building 1A
Stanford, CA 94305-9010
Tel: (650)725-2593
FAX: (650)725-1449
email:
ang@cs.stanford.edu
Research interests: Machine learning and pattern recognition, statistical artificial intelligence, reinforcement learning and adaptive control. algorithms for text and web data processing.
Reinforcement learning videos. (Autonomous helicopter, quadruped climbing over obstacles, high-speed obstacle avoidance, etc.)
Teaching:
CS229: Machine Learning, Autumn 2004.
CS221: Artificial Intelligence: Principles and Techniques, Autumn 2004.
Learning Depth from Single Monocular Images,
Ashutosh Saxena, Sung Chung, and Andrew Y. Ng.
To appear in NIPS 2005.
[ps, pdf coming soon]
Learning vehicular dynamics, with application to modeling helicopters,
Pieter Abbeel, Varun Ganapathi and Andrew Y. Ng.
To appear in NIPS 2005.
[ps, pdf coming soon]
On Local Rewards and the Scalability of Distributed Reinforcement Learning,
J. Andrew Bagnell and Andrew Y. Ng.
To appear in NIPS 2005.
[ps, pdf coming soon]
Meta-learning for text classification,
Chuong Do and Andrew Y. Ng.
To appear in NIPS 2005.
[ps, pdf coming soon]
Fast Gaussian Process Regression using KD-trees,
Yirong Shen, Andrew Y. Ng and Matthias Seeger.
To appear in NIPS 2005.
[ps, pdf coming soon]
Robust Textual Inference via Graph Matching,
Aria Haghighi, Andrew Y. Ng and Chris Manning.
To appear in Proceedings of the Human Language Technology Conference/Empirical Methods in Natural Language Processing (HLT-EMNLP), 2005.
[ps,
pdf]
High-speed obstacle avoidance using monocular vision and reinforcement learning,
Jeff Michels, Ashutosh Saxena and Andrew Y. Ng.
To appear in Proceedings of the Twenty-first International Conference on Machine Learning, 2005.
[ps, pdf]
Exploration and apprenticeship learning in reinforcement learning,
Pieter Abbeel and Andrew Y. Ng.
To appear in Proceedings of the Twenty-first International Conference on Machine Learning, 2005.
[ps, pdf]
Robust textual inference via learning and abductive reasoning,
Rajat Raina, Andrew Y. Ng and Chris Manning.
To appear in Proceedings of the Twentieth National Conference on Artificial Intelligence (AAAI), 2005.
[ps, pdf]
Spam deobfuscation using a hidden Markov model,
Honglak Lee and and Andrew Y. Ng.
To appear in Proceedings of the Second Conference on Email and Anti-Spam, 2005.
[ps, pdf]
Learning factor graphs in polynomial time & sample complexity,
Pieter Abbeel, Daphne Koller and Andrew Y. Ng.
To appear in Proceedings of the Twenty-first Conference on Uncertainty in Artificial Intelligence, 2005.
[ps, pdf]
Discriminative Learning of Markov Random Fields for Segmentation of 3D Range Data,
Drago Anguelov, Ben Taskar, Vasco Chatalbashev, Daphne Koller, Dinkar Gupta, Geremy Heitz and Andrew Y. Ng.
To appear in Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), 2005.
[ps, pdf]
Discriminative training of Kalman filters,
Pieter Abbeel, Adam Coates, Mike Montemerlo, Andrew Y. Ng and Sebastian Thrun.
To appear in Proceedings of Robotics: Science and Systems, 2005.
[ps, pdf coming soon]
Autonomous Helicopter Tracking and Localization Using a Self-Calibrating Camera Array,
Masa Matsuoka, Surya Singh, Alan Chen, Adam Coates, Andrew Y. Ng and Sebastian Thrun.
To appear in Proceedings of the Fifth International Conference on Field Service Robotics, 2005.
[ps, pdf coming soon]
Stable adaptive control with online learning, Andrew Y. Ng and H. Jin Kim. In NIPS 17, 2005. [ps, pdf]
Learning syntactic patterns for automatic hypernym discovery, Rion Snow, Dan Jurafsky and Andrew Y. Ng. In NIPS 17, 2005. [ps, pdf]
Online bounds for Bayesian algorithms, Sham Kakade and Andrew Y. Ng. In NIPS 17, 2005. [ps, pdf]
Learning first order Markov models for control, Pieter Abbeel and Andrew Y. Ng. In NIPS 17, 2005. [ps, pdf]
Inverted autonomous helicopter flight via reinforcement learning, Andrew Y. Ng, Adam Coates, Mark Diel, Varun Ganapathi, Jamie Schulte, Ben Tse, Eric Berger and Eric Liang. In International Symposium on Experimental Robotics, 2004. [ps, pdf]
Apprenticeship learning via inverse reinforcement learning, Pieter Abbeel and Andrew Y. Ng. In Proceedings of the Twenty-first International Conference on Machine Learning, 2004. [ps, pdf]
Feature selection, L1 vs. L2 regularization, and rotational invariance, Andrew Y. Ng. In Proceedings of the Twenty-first International Conference on Machine Learning, 2004. [ps, pdf]
Learning random walk models for inducing word dependency probabilities, Kristina Toutanova, Christopher Manning and Andrew Y. Ng. In Proceedings of the Twenty-first International Conference on Machine Learning, 2004. [ps, pdf]
Online learning of pseudo-metrics, Shai Shalev-Shwartz, Yoram Singer and Andrew Y. Ng. In Proceedings of the Twenty-first International Conference on Machine Learning, 2004. [ps, pdf]
Policy search by dynamic programming, J. Andrew Bagnell, Sham Kakade, Andrew Y. Ng and Jeff Schneider, In NIPS 16, 2004. [ps, pdf]
Classification with Hybrid Generative/Discriminative Models, Rajat Raina, Yirong Shen, Andrew Y. Ng and Andrew McCallum, In NIPS 16, 2004. [ps, pdf]
Latent Dirichlet Allocation, David Blei, Andrew Y. Ng and Michael Jordan. Journal of Machine Learning Research, 3:993-1022, 2003. [ps, pdf]
Distance metric learning, with application to clustering with side-information, Eric Xing, Andrew Y. Ng, Michael Jordan, and Stuart Russell. In NIPS 15, 2003. [ps, pdf]
On Discriminative vs. Generative Classifiers: A comparison of logistic regression and Naive Bayes, Andrew Y. Ng and Michael Jordan. In NIPS 14,, 2002. [ps, pdf]
On Spectral Clustering: Analysis and an algorithm, Andrew Y. Ng, Michael Jordan, and Yair Weiss. In NIPS 14,, 2002. [ps, pdf]
Latent Dirichlet Allocation, David Blei, Andrew Y. Ng, and Michael Jordan. In NIPS 14,, 2002. [ps, pdf]
Link analysis, eigenvectors, and stability, Andrew Y. Ng, Alice X. Zheng and Michael Jordan. In Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence (IJCAI-01), 2001. [ps, pdf]
Stable algorithms for link analysis, Andrew Y. Ng, Alice X. Zheng and Michael Jordan. In Proceedings of the Twenty-fourth Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2001. [ps, pdf]
Convergence rates of the Voting Gibbs classifier, with application to Bayesian feature selection, Andrew Y. Ng and Michael Jordan. In Proceedings of the Eighteenth International Conference on Machine Learning, 2001. [ps, pdf]
PEGASUS: A policy search method for large MDPs and POMDPs, Andrew Y. Ng and Michael Jordan. In Uncertainty in Artificial Intelligence, Proceedings of the Sixteenth Conference, 2000. [ps, pdf]
Algorithms for inverse reinforcement learning, Andrew Y. Ng and Stuart Russell. In Proceedings of the Seventeenth International Conference on Machine Learning, 2000. [ps, pdf]
Approximate inference algorithms for two-layer Bayesian networks, Andrew Y. Ng and Michael Jordan. In NIPS 12, 2000. [ps, pdf]
Policy search via density estimation, Andrew Y. Ng, Ronald Parr and Daphne Koller. In NIPS 12, 2000. [ps, pdf]
Approximate planning in large POMDPs via reusable trajectories, Michael Kearns, Yishay Mansour and Andrew Y. Ng. In NIPS 12, 2000. [ps, pdf]. A long version is also available. [ps, pdf]
Policy invariance under reward transformations: Theory and application to reward shaping, Andrew Y. Ng, Daishi Harada and Stuart Russell. In Proceedings of the Sixteenth International Conference on Machine Learning, 1999. [ps, pdf]
A sparse sampling algorithm for near-optimal planning in large Markov decision processes, Michael Kearns, Yishay Mansour and Andrew Y. Ng. In Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence (IJCAI-99), 1999. [ps, pdf]. Long version to appear in Machine Learning.
On Feature Selection: Learning with Exponentially many Irrelevant Features as Training Examples, Andrew Y. Ng. In Proceedings of the Fifteenth International Conference on Machine Learning, 1998. [ps, pdf]
Applying Online-search to Reinforcement Learning, Scott Davies, Andrew Y. Ng and Andrew Moore. In Proceedings of the Fifteenth National Conference on Artificial Intelligence (AAAI-98), 1998. [ps, pdf]. An earlier version had also been presented at the Workshop on Reinforcement Learning at ICML97, 1997. [ps, pdf]
Improving Text Classification by Shrinkage in a Hierarchy of Classes, Andrew McCallum, Roni Rosenfeld, Tom Mitchell and Andrew Y. Ng in Proceedings of the Fifteenth International Conference on Machine Learning, 1998. [ps, pdf]
Preventing "Overfitting" of Cross-Validation data, Andrew Y. Ng, in Proceedings of the Fourteenth International Conference on Machine Learning, 1997. [ps, pdf]
An Information-Theoretic Analysis of Hard and Soft Assignment Methods for Clustering, Michael Kearns, Yishay Mansour and Andrew Y. Ng, in Proceedings of the Thirteenth Annual Conference on Uncertainty in Artificial Intelligence, 1997. [ps, pdf]. Also a book chapter in Learning in Graphical Models, Ed. Michael Jordan, 1998.
An Experimental and Theoretical Comparison of Model Selection Methods, Michael Kearns, Yishay Mansour, Andrew Y. Ng and Dana Ron, in Machine Learning 27(1), pp. 7-50, 1997. [pdf]. A shorter version had also appeard in Proceedings of the Eigth Annual ACM Conference on Computational Learning Theory, 1995. [ps, pdf].
ML Papers: search engine for online Machine Learning papers.
Vision Papers: search engine for online Vision papers.
The Haystack Project.
(David Karger and
Lynn Stein)
AT&T Labs - Research.
The Autonomous Machine Learning Lab (AUTON) at Carnegie Mellon University.