Bio

Bio


Professor Ng's research is in the areas of machine learning and artificial intelligence.

He leads the STAIR (STanford Artificial Intelligence Robot) project, whose goal is to develop a home assistant robot that can perform tasks such as tidy up a room, load/unload a dishwasher, fetch and deliver items, and prepare meals using a kitchen. Since its birth in 1956, the AI dream has been to build systems that exhibit broad spectrum intelligence. However, AI has since splintered into many different subfields, such as machine learning, vision, navigation, reasoning, planning, and natural language processing. To realize its vision of a home assistant robot, STAIR will unify into a single platform tools drawn from all of these AI subfields. This is in distinct contrast to the 30-year-old trend of working on fragmented AI sub-fields, so that STAIR is also a unique vehicle for driving forward research towards true, integrated AI.

Ng also works on machine learning algorithms for robotic control, in which rather than relying on months of human hand-engineering to design a controller, a robot instead learns automatically how best to control itself. Using this approach, Ng's group has developed by far the most advanced autonomous helicopter controller that is capable of flying spectacular aerobatic maneuvers that even experienced human pilots often find extremely difficult to execute. As part of this work, Ng's group also developed algorithms that can take a single image and turn the picture into a 3-D model that one can fly-through and see from different angles.

Academic Appointments


Honors & Awards


  • Alfred P. Sloan Fellowship, Alfred P. Sloan Foundation (2007)

Professional Education


  • PhD, UC Berkeley (2002)

Teaching

2014-15 Courses


Publications

All Publications


  • Learning random walk models for inducing word dependency probabilities Ng, Andrew, Y.
  • Long-term outcome for gastric marginal zone lymphoma treated with radiotherapy: a retrospective, multi-centre, International Extranodal Lymphoma Study Group study ANNALS OF ONCOLOGY Wirth, A., Gospodarowicz, M., Aleman, B. M., Bressel, M., Ng, A., Chao, M., Hoppe, R. T., Thieblemont, C., Tsang, R., Moser, L., Specht, L., Szpytma, T., Lennard, A., Seymour, J. F., Zucca, E. 2013; 24 (5): 1344-1351

    Abstract

    We evaluated the long-term results of radiotherapy for patients with gastric marginal zone lymphoma (GMZL).We carried out a retrospective, multi-centre study of patients with low-grade GMZL treated by radiotherapy between 17 July 1981 and 25 March 2004.There were 102 eligible patients. Fifty-eight patients were previously untreated and 44 had recurrent/residual disease after prior treatment (HP eradication, chemotherapy and surgery in 35, 9 and 8 patients, respectively, and 7 had >1 prior therapy). Radiation fields included the stomach /involved nodes in 61 patients and whole abdomen in 41. The median radiotherapy dose to stomach was 40 Gy (range 26-46 Gy) in a median 22 fractions. With a median follow-up after radiotherapy of 7.9 years (range 0.3-24 years), 10- and 15-year freedom from treatment failure (FFTF) was 88% (95% CI 82%-95%). Risk factors for TF were a large-cell component (P = 0.036) and an exophytic growth pattern (P = 0.042). Radiotherapy field size, radiotherapy dose, and failure of prior therapy were not associated with inferior FFTF. Ten-year overall survival was 70% (95% CI 60%-82%).Radiotherapy achieves cure for the majority of patients with low-grade GMZL, including patients who have had prior therapy. Several features may predict a poorer outcome.

    View details for DOI 10.1093/annonc/mds623

    View details for Web of Science ID 000318105000028

  • Learning New Facts From Knowledge Bases With Neural Tensor Networks and Semantic Word Vectors in ICLR Chen, D., Socher, R., Manning, Christopher, D., Ng, Andrew, Y. 2013
  • Deep Learning with COTS HPC Systems in ICML Coates, A., Huval, B., Wang, T., Wu, David, J., Catanzaro, B., Ng, Andrew, Y. 2013
  • Parsing with Compositional Vector Grammars in ACL Bauer, J., Socher, R., Manning, Christopher, D., Ng, Andrew, Y. 2013
  • A simple intervention to reinforce awareness of tanning bed use and skin cancer in non-medical skin care professionals in Southern California INTERNATIONAL JOURNAL OF DERMATOLOGY Ng, A. T., Chang, A. L., Cockburn, M., Peng, D. H. 2012; 51 (11): 1307-1312

    Abstract

    (i) To assess the baseline knowledge of non-medical skin care professionals (estheticians, cosmetologists, massage therapists) on tanning bed use and its association with melanoma; and (ii) to provide preliminary evidence of the potential impact of a fast and simple educational intervention on tanning beds and melanoma on the awareness of non-medical skin care professionals towards skin cancer prevention.A pre-intervention survey was administered to non-medical skin care professional at salons or spas in Southern California to assess baseline knowledge on tanning and skin cancer. This was followed immediately by a 10-minute oral presentation on tanning bed use and its association with melanoma. One month later, a post-intervention survey was distributed to individuals who attended the initial oral presentation.Significant changes pre- and post-intervention were found in non-medical skin care professionals' answer responses to the following: (i) increased speaking to clients about cancer risk with tanning bed use 42-66% (OR 2.44; 95% CI 1.39, 4.30)]; (ii) decreased personal tanning bed use (23-15% [OR 0.61; 95% CI 0.37, 1.00]); and (iii) decreased belief that tanning beds are an excellent cosmetic tool (29-20% [OR 0.60; 95% CI 0.38, 0.96]).This study provides preliminary evidence that non-medical skin care professionals could be an important source of primary prevention information for reducing the burden of melanoma.

    View details for DOI 10.1111/j.1365-4632.2011.05425.x

    View details for Web of Science ID 000310272600006

    View details for PubMedID 23067078

  • Recurrent Neural Networks for Noise Reduction in Robust ASR 13TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2012 (INTERSPEECH 2012), VOLS 1-3 Maas, A. L., Le, Q. V., O'Neil, T. M., Vinyals, O., Nguyen, P., Ng, A. Y. 2012: 22-25
  • Building High-Level Features using Large Scale Unsupervised Learning in ICML Le, Quoc, V., Ranzato, M., Monga, R., Devin, M., Chen, K., Corrado, Greg, S. 2012
  • End-to-End Text Recognition with Convolutional Neural Networks in ICPR Wang, T., Wu, David, J., Coates, A., Ng, Andrew, Y. 2012
  • Emergence of Object-Selective Features in Unsupervised Feature Learning. in NIPS Coates, A., Karpathy, A. 2012
  • Learning Feature Representations with K-means. in Neural Networks: Tricks of the Trade, Reloaded, Springer LNCS Coates, A., Ng, Andrew, Y. 2012
  • Convolutional-Recursive Deep Learning for 3D Object Classification. in NIPS Socher, R., Huval, B., Bhat, B., Manning, Christopher, D., Ng, Andrew, Y. 2012
  • Semantic Compositionality through Recursive Matrix-Vector Spaces in EMNLP Socher, R., Huval, B., Manning, Christopher, D., Ng, Andrew, Y. 2012
  • Improving Word Representations via Global Context and Multiple Word Prototypes in ACL Huang, Eric, H., Socher, R., Manning, Christopher, D., Ng, Andrew, Y. 2012
  • Deep Learning of Invariant Features via Simulated Fixations in Video in NIPS Zou, Will, Y., Zhu, S., Ng, Andrew, Y., Yu, K. 2012
  • Word-level Acoustic Modeling with Convolutional Vector Regression Learning Workshop in ICML Maas, Andrew, L., Miller, Stephen, D., O'Neil, Tyler, M., Ng, Andrew, Y. 2012
  • Large Scale Distributed Deep Networks. in NIPS Dean, J., Corrado, G., S., Monga, R., Chen, K., Devin, M., Le, Q., V. 2012
  • Unsupervised Learning of Hierarchical Representations with Convolutional Deep Belief Networks COMMUNICATIONS OF THE ACM Lee, H., Grosse, R., Ranganath, R., Ng, A. Y. 2011; 54 (10): 95-103
  • ACR Appropriateness Criteria (R) on Hodgkin's Lymphoma-Unfavorable Clinical Stage I and II JOURNAL OF THE AMERICAN COLLEGE OF RADIOLOGY Das, P., Ng, A., Constine, L. S., Advani, R., Flowers, C., Friedberg, J., Hodgson, D. C., Schwartz, C. L., Wilder, R. B., Wilson, L. D., Yunes, M. J. 2011; 8 (5): 302-308

    Abstract

    Combined-modality therapy, consisting of chemotherapy followed by radiation therapy (RT), represents the standard of care for most patients with unfavorable-prognosis early-stage Hodgkin's lymphoma. The most widely accepted chemotherapy regimen is ABVD (Adriamycin, bleomycin, vinblastine, and dacarbazine); however, recent trials have evaluated other regimens such as BEACOPP (bleomycin, etoposide, doxorubicin, cyclophosphamide, vincristine, procarbazine, and prednisone) and Stanford V. After chemotherapy, the standard radiation field is involved-field RT, although there is increasing interest now in involved-node RT. The authors review recent trials on chemotherapy and RT for unfavorable-prognosis early-stage Hodgkin's lymphoma. This article presents illustrative clinical cases, with treatment recommendations from an expert panel of radiation oncologists and medical oncologists.

    View details for DOI 10.1016/j.jacr.2011.01.009

    View details for Web of Science ID 000306201300006

    View details for PubMedID 21531305

  • Calciphylaxis DERMATOLOGIC THERAPY Ng, A. T., Peng, D. H. 2011; 24 (2): 256-262

    Abstract

    Calciphylaxis is a disease in which metastatic calcification affects small- and medium-sized vessels resulting in significant dermatologic manifestations. Lesions typically occur over areas of high fat content and progress to black leathery eschars. Calciphylaxis is associated with intense pain and markedly increased risk of infection, often leading to sepsis requiring hospitalization. Diagnosis is made by clinical history and skin biopsy. Management of calciphylaxis is interdisciplinary, emphasizing factors such as primary prevention, proper wound care, pain control, and hormone and mineral balance. Although calciphylaxis carries a high mortality rate, symptomatic treatment has shown promise as a method for controlling disease progression.

    View details for DOI 10.1111/j.1529-8019.2011.01401.x

    View details for Web of Science ID 000288455800011

    View details for PubMedID 21410615

  • Getting the word out: A fast intervention to educate nonmedical skin care professionals at salons and spas in southern California about tanning bed usage and skin cancer Ng, A., Chang, A. L., Peng, D. MOSBY-ELSEVIER. 2011: AB78-AB78
  • The Stanford LittleDog: A learning and rapid replanning approach to quadruped locomotion INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH Kolter, J. Z., Ng, A. Y. 2011; 30 (2): 150-174
  • Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis 2011 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) Le, Q. V., Zou, W. Y., Yeung, S. Y., Ng, A. Y. 2011
  • A Low-cost Compliant 7-DOF Robotic Manipulator 2011 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA) Quigley, M., Asbeck, A., Ng, A. 2011
  • Grasping with Application to an Autonomous Checkout Robot 2011 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA) Klingbeil, E., Rao, D., Carpenter, B., Ganapathi, V., Ng, A. Y., Khatib, O. 2011
  • Unsupervised Learning Models of Primary Cortical Receptive Fields and Receptive Field Plasticity in NIPS Saxe, A., Bhand, M., Mudur, R., Suresh, B., Ng, Andrew, Y. 2011
  • Sparse Filtering in NIPS Ngiam, J., Koh, P., Chen, Z., Bhaskar, S., Ng, Andrew, Y. 2011
  • Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions in EMNLP Socher, R., Pennington, J., Huang, E., Ng, Andrew, Y. 2011
  • Selecting Receptive Fields in Deep Networks in NIPS Coates, A., Ng, Andrew, Y. 2011
  • On Random Weights and Unsupervised Feature Learning in ICML Saxe, A., Koh, P., Chen, Z., Bhand, M., Suresh, B., Ng, Andrew, Y. 2011
  • Multimodal Deep Learning in ICML Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., Ng, Andrew, Y. 2011
  • Learning Deep Energy Models in ICML Ngiam, J., Chen, Z., Koh, P., Ng, Andrew, Y. 2011
  • Dynamic Pooling and Unfolding Recursive Autoencoders for Paraphrase Detection in NIPS Socher, R., Huang, Eric, H., Pennington, J., Ng, Andrew, Y. 2011
  • Autonomous Sign Reading for Semantic Mapping 2011 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA) Case, C., Suresh, B., Coates, A., Ng, A. Y. 2011
  • The Importance of Encoding Versus Training with Sparse Coding and Vector Quantization in ICML Coates, A., Ng, Andrew, Y. 2011
  • Parsing Natural Scenes and Natural Language with Recursive Neural Networks in ICML Socher, R., Lin, C., Ng, Andrew, Y., Manning, C. 2011
  • Learning Word Vectors for Sentiment Analysis in ACL Maas, Andrew, L., Daly, Raymond, E., Pham, Peter, T., Huang, D., Ng, Andrew, Y. 2011
  • ICA with Reconstruction Cost for Efficient Overcomplete Feature Learning in NIPS Le, Quoc, V., Karpenko, A., Ngiam, J., Ng, Andrew, Y. 2011
  • Text Detection and Character Recognition in Scene Images with Unsupervised Feature Learning in ICDAR Coates, A., Carpenter, B., Case, C., Satheesh, S., Suresh, B., Wang, T. 2011
  • An Analysis of Single-Layer Networks in Unsupervised Feature Learning in AISTATS Coates, A., Lee, H., Ng, A. 2011; 14
  • On Optimization Methods for Deep Learning in ICML Le, Quoc, V., Ngiam, J., Coates, A., Lahiri, A., Prochnow, B., Ng, Andrew, Y. 2011
  • Autonomous Helicopter Aerobatics through Apprenticeship Learning INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH Abbeel, P., Coates, A., Ng, A. Y. 2010; 29 (13): 1608-1639
  • Ubiquitin accumulation in autophagy-deficient mice is dependent on the Nrf2-mediated stress response pathway: a potential role for protein aggregation in autophagic substrate selection JOURNAL OF CELL BIOLOGY Riley, B. E., Kaiser, S. E., Shaler, T. A., Ng, A. C., Hara, T., Hipp, M. S., Lage, K., Xavier, R. J., Ryu, K. Y., Taguchi, K., Yamamoto, M., Tanaka, K., Mizushima, N., Komatsu, M., Kopito, R. R. 2010; 191 (3): 537-552

    Abstract

    Genetic ablation of autophagy in mice leads to liver and brain degeneration accompanied by the appearance of ubiquitin (Ub) inclusions, which has been considered to support the hypothesis that ubiquitination serves as a cis-acting signal for selective autophagy. We show that tissue-specific disruption of the essential autophagy genes Atg5 and Atg7 leads to the accumulation of all detectable Ub-Ub topologies, arguing against the hypothesis that any particular Ub linkage serves as a specific autophagy signal. The increase in Ub conjugates in Atg7(-/-) liver and brain is completely suppressed by simultaneous knockout of either p62 or Nrf2. We exploit a novel assay for selective autophagy in cell culture, which shows that inactivation of Atg5 leads to the selective accumulation of aggregation-prone proteins, and this does not correlate with an increase in substrate ubiquitination. We propose that protein oligomerization drives autophagic substrate selection and that the accumulation of poly-Ub chains in autophagy-deficient circumstances is an indirect consequence of activation of Nrf2-dependent stress response pathways.

    View details for DOI 10.1083/jcb.201005012

    View details for Web of Science ID 000284135700012

    View details for PubMedID 21041446

  • Grasping Novel Objects with Depth Segmentation IEEE/RSJ 2010 INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2010) Rao, D., Le, Q. V., Phoka, T., Quigley, M., Sudsang, A., Ng, A. Y. 2010: 2578-2585
  • Energy Disaggregation via Discriminative Sparse Coding in NIPS Kolter, J., Zico, Ng, Andrew, Y. 2010
  • Tiled Convolutional Neural Networks in NIPS Le, Quoc, V., Ngiam, J., Chen, Z., Chia, D., Koh, P., Ng, Andrew, Y. 2010
  • A Probabilistic Model for Semantic Word Vectors in NIPS Maas, A., Ng, A. 2010
  • Multi-Camera Object Detection for Robotics in ICRA Coates, A., Ng, Andrew, Y. 2010
  • Learning Continuous Phrase Representations and Syntactic Parsing with Recursive Neural Networks in NIPS Socher, R., Manning, C., Ng, A. 2010
  • Learning to Open New Doors IEEE/RSJ 2010 INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2010) Klingbeil, E., Saxena, A., Ng, A. Y. 2010
  • Learning to grasp objects with multiple contact points 2010 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA) Le, Q. V., Kamm, D., Kara, A. F., Ng, A. Y. 2010: 5062-5069
  • A Probabilistic Approach to Mixed Open-loop and Closed-loop Control, with Application to Extreme Autonomous Driving 2010 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA) Kolter, J. Z., Plagemann, C., Jackson, D. T., Ng, A. Y., Thrun, S. 2010: 839-845
  • A Vision-Based System for Grasping Novel Objects in Cluttered Environments ROBOTICS RESEARCH Saxena, A., Wong, L., Quigley, M., Ng, A. Y. 2010; 66: 337-348
  • A Steiner tree approach to efficient object detection 2010 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) Russakovsky, O., Ng, A. Y. 2010: 1070-1077
  • Low-cost Accelerometers for Robotic Manipulator Perception IEEE/RSJ 2010 INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2010) Quigley, M., Brewer, R., Soundararaj, S. P., Pradeep, V., Le, Q., Ng, A. Y. 2010
  • Autonomous Operation of Novel Elevators for Robot Navigation 2010 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA) Klingbeil, E., Carpenter, B., Russakovsky, O., Ng, A. Y. 2010: 751-758
  • Multi-Camera Object Detection for Robotics 2010 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA) Coates, A., Ng, A. Y. 2010: 412-419
  • Guest editorial: Special issue on robot learning, Part B AUTONOMOUS ROBOTS Peters, J., Ng, A. Y. 2009; 27 (2): 91-92
  • Apprenticeship Learning for Helicopter Control COMMUNICATIONS OF THE ACM Coates, A., Abbeel, P., Ng, A. Y. 2009; 52 (7): 97-105
  • Guest editorial: Special issue on robot learning, Part A AUTONOMOUS ROBOTS Peters, J., Ng, A. Y. 2009; 27 (1): 1-2
  • Make3D: Learning 3D Scene Structure from a Single Still Image IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE Saxena, A., Sun, M., Ng, A. Y. 2009; 31 (5): 824-840

    Abstract

    We consider the problem of estimating detailed 3D structure from a single still image of an unstructured environment. Our goal is to create 3D models that are both quantitatively accurate as well as visually pleasing. For each small homogeneous patch in the image, we use a Markov Random Field (MRF) to infer a set of "plane parameters" that capture both the 3D location and 3D orientation of the patch. The MRF, trained via supervised learning, models both image depth cues as well as the relationships between different parts of the image. Other than assuming that the environment is made up of a number of small planes, our model makes no explicit assumptions about the structure of the scene; this enables the algorithm to capture much more detailed 3D structure than does prior art and also give a much richer experience in the 3D flythroughs created using image-based rendering, even for scenes with significant nonvertical structure. Using this approach, we have created qualitatively correct 3D models for 64.9 percent of 588 images downloaded from the Internet. We have also extended our model to produce large-scale 3D models from a few images.

    View details for DOI 10.1109/TPAMI.2008.132

    View details for Web of Science ID 000264144500005

    View details for PubMedID 19299858

  • Inherited disorders affecting mitochondrial function are associated with glutathione deficiency and hypocitrullinemia PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA Atkuri, K. R., Cowan, T. M., Kwan, T., Ng, A., Herzenberg, L. A., Herzenberg, L. A., Enns, G. M. 2009; 106 (10): 3941-3945

    Abstract

    Disorders affecting mitochondria, including those that directly affect the respiratory chain function or result from abnormalities in branched amino acid metabolism (organic acidemias), have been shown to be associated with impaired redox balance. Almost all of the evidence underlying this conclusion has been obtained from studies on patient biopsies or animal models. Since the glutathione (iGSH) system provides the main protection against oxidative damage, we hypothesized that untreated oxidative stress in individuals with mitochondrial dysfunction would result in chronic iGSH deficiency. We confirm this hypothesis here in studies using high-dimensional flow cytometry (Hi-D FACS) and biochemical analysis of freshly obtained blood samples from patients with mitochondrial disorders or organic acidemias. T lymphocyte subsets, monocytes and neutrophils from organic acidemia and mitochondrial patients who were not on antioxidant supplements showed low iGSH levels, whereas similar subjects on antioxidant supplements showed normal iGSH. Measures of iROS levels in blood were insufficient to reveal the chronic oxidative stress in untreated patients. Patients with organic acidemias showed elevated plasma protein carbonyls, while plasma samples from all patients tested showed hypocitrullinemia. These findings indicate that measurements of iGSH in leukocytes may be a particularly useful biomarker to detect redox imbalance in mitochondrial disorders and organic acidemias, thus providing a relatively non-invasive means to monitor disease status and response to therapies. Furthermore, studies here suggest that antioxidant therapy may be useful for relieving the chronic oxidative stress that otherwise occurs in patients with mitochondrial dysfunction.

    View details for DOI 10.1073/pnas.0813409106

    View details for Web of Science ID 000264036900054

    View details for PubMedID 19223582

  • Joint calibration of multiple sensors 2009 IEEE-RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS Quoc V Le, Q. V., Ng, A. Y. 2009: 3651-3658
  • Near-Bayesian Exploration in Polynomial Time in ICML Kolter, J., Zico, Ng, Andrew, Y. 2009
  • Large-scale Deep Unsupervised Learning using Graphics Processors in ICML Raina, R., Madhavan, A., Ng, Andrew, Y. 2009
  • Convolutional Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations in ICML Lee, H., Grosse, R., Ranganath, R., Ng, Andrew, Y. 2009
  • Measuring Invariances in Deep Networks in NIPS Goodfellow, Ian, J., Le, Quoc, V., Saxe, Andrew, M., Lee, H., Ng, Andrew, Y. 2009
  • Unsupervised Feature Learning for Audio Classification Using Convolutional Deep Belief Networks in NIPS Lee, H., Largman, Y., Pham, P., Ng, Andrew, Y. 2009
  • A majorization-minimization algorithm for (multiple) hyperparameter learning in ICML Foo, C. S., Do, C., Ng, Andrew, Y. 2009
  • ROS: An Open-Source Robot Operating System in ICRA Quigley, M., Gerkey, B., Conley, K., Faust, J., Foote, T., Leibs, J., Ng, A. 2009
  • Regularization and Feature Selection in Least-Squares Temporal Difference Learning in ICML Kolter, J., Zico, Ng, Andrew, Y. 2009
  • Policy Search via the Signed Derivative in RSS Kolter, J., Zico, Ng, Andrew, Y. 2009
  • Task-Space Trajectories via Cubic Spline Optimization ICRA: 2009 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-7 Kolter, J. Z., Ng, A. Y. 2009: 2364-2371
  • Learning Sound Location from a Single Microphone ICRA: 2009 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-7 Saxena, A., Ng, A. Y. 2009: 4310-4315
  • Reactive Grasping Using Optical Proximity Sensors ICRA: 2009 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-7 Hsiao, K., Nangeroni, P., Huber, M., Saxena, A., Ng, A. Y. 2009: 4230-4237
  • Learning 3-D Object Orientation from Images ICRA: 2009 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-7 Saxena, A., Driemeyer, J., Ng, A. Y. 2009: 4266-4272
  • Scalable Learning for Object Detection with GPU Hardware 2009 IEEE-RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS Coates, A., Baumstarck, P., Le, Q., Ng, A. Y. 2009: 4287-4293
  • Autonomous Autorotation of an RC Helicopter EXPERIMENTAL ROBOTICS Abbeel, P., Coates, A., Hunter, T., Ng, A. Y. 2009; 54: 385-394
  • High-Accuracy 3D Sensing for Mobile Manipulation: Improving Object Detection and Door Opening ICRA: 2009 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-7 Quigley, M., Batra, S., Gould, S., Klingbeil, E., Le, Q., Wellman, A., Ng, A. Y. 2009: 3604-3610
  • Exponential Family Sparse Coding with Applications to Self-taught Learning 21ST INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE (IJCAI-09), PROCEEDINGS Lee, H., Raina, R., Teichman, A., Ng, A. Y. 2009: 1113-1119
  • Stereo Vision and Terrain Modeling for Quadruped Robots ICRA: 2009 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-7 Kolter, J. Z., Kim, Y., Ng, A. Y. 2009: 3894-3901
  • Robotic grasping of novel objects using vision INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH Saxena, A., Driemeyer, J., Ng, A. Y. 2008; 27 (2): 157-173
  • 3-d depth reconstruction from a single still image INTERNATIONAL JOURNAL OF COMPUTER VISION Saxena, A., Chung, S. H., Ng, A. Y. 2008; 76 (1): 53-69
  • Cheap and Fast – But Is It Good? Evaluating Non-Expert Annotations for Natural Language Tasks in EMNLP Snow, R., O'Connor, B., Jurafsky, D., Ng, Andrew, Y. 2008
  • Make3D: Depth Perception from a Single Still Image in AAAI Saxena, A., Sun, M. 2008
  • Learning Grasp Strategies with Partial Shape Information in AAAI Saxena, A., Wong, L. 2008
  • Space-Indexed Dynamic Programming: Learning to Follow Trajectories in ICML Kolter, J., Zico, Coates, A., Ng, Andrew, Y., Gu, Y. 2008
  • Learning for Control from Multiple Demonstrations in ICML Coates, A., Abbeel, P., Ng, Andrew, Y. 2008
  • Integrating Visual and Range Data for Robotic Object Detection in M2SFA2 Gould, S., Baumstarck, P., Quigley, M., Ng, Andrew, Y., DuHadway, D. 2008
  • A Fast Data Collection and Augmentation Procedure for Object Recognition in AAAI Sapp, B., Saxena, A. 2008
  • Learning to grasp novel objects using vision EXPERIMENTAL ROBOTICS Saxena, A., Driemeyer, J., Kearns, J., Osondu, C., Ng, A. Y. 2008; 39: 33-42
  • A control architecture for quadruped locomotion over rough terrain 2008 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-9 Kolter, J. Z., Rodgers, M. R., Ng, A. Y. 2008: 811-818
  • Apprenticeship Learning for Motion Planning with Application to Parking Lot Navigation 2008 IEEE/RSJ INTERNATIONAL CONFERENCE ON ROBOTS AND INTELLIGENT SYSTEMS, VOLS 1-3, CONFERENCE PROCEEDINGS Abbeel, P., Dolgov, D., Ng, A. Y., Thrun, S. 2008: 1083-1090
  • Autonomous helicopter tracking and localization using a self-surveying camera array Matsuoka, M., Chen, A., Singh, S. P., Coates, A., Ng, A. Y., Thrun, S. SAGE PUBLICATIONS LTD. 2007: 205-215
  • Automatic single-image 3D reconst ruct ions of indoor Manhattan world scenes ROBOTICS RESEARCH Delage, E., Lee, H., Ng, A. Y. 2007; 28: 305-321
  • Learning Omnidirectional Path Following Using Dimensionality Reduction Kolter, J., Zico, Ng, Andrew, Y. edited by Karamcheti, K. 2007
  • Shift-Invariant Sparse Coding for Audio Classification Grosse, R., Raina, R., Kwong, H., Ng, Andrew, Y. 2007
  • Sparse Deep Belief Net Model for Visual Area V2 in NIPS Lee, H., Chaitanya, E. 2007
  • Map-Reduce for Machine Learning on Multicore in NIPS Chu, C., Kim, S. K., Lin, Y. 2007; 19
  • Hierarchical Apprenticeship Learning with Applications to Quadruped Locomotion in NIPS Kolter, J., Zico, Abbeel, P. 2007
  • Efficient Sparse Coding Algorithms in NIPS Lee, H., Battle, A., Rajat, R., Ng, Andrew, Y. 2007; 19
  • Efficient multiple hyperparameter learning for log-linear models in NIPS Do, C., Foo, C., Ng, Andrew, Y. 2007
  • An Application of Reinforcement Learning to Aerobatic Helicopter Flight in NIPS Abbeel, P., Coates, A., Quigley, M., Ng, Andrew, Y. 2007; 19
  • Portable GNSS Baseband Logging in GNSS Quigley, M., Abbeel, P., De Lorenzo, Dave, S., Gu, Y., Bolouki, S., Akos, D., Ng, A. 2007
  • Self-Taught Learning: Transfer Learning from Unlabeled Data in ICML Raina, R., Battle, A., Lee, H., Packer, B., Ng, Andrew, Y. 2007
  • Robotic Grasping of Novel Objects in NIPS Saxena, A., Driemeyer, J., Kearns, J., Ng, Andrew, Y. 2007; 19
  • Learning to merge word senses in EMNLP Snow, R., Prakash, S., Jurafsky, D., Ng, Andrew, Y. 2007
  • A Factor Graph Model for Software Bug Finding 20TH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE Kremenek, T., Ng, A. Y., Engler, D. 2007: 2510-2516
  • Learning 3-d scene structure from a single still image 2007 IEEE 11TH INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOLS 1-6 Saxena, A., Sun, M., Ng, A. Y. 2007: 1-8
  • 3-d reconstruction from sparse views using monocular vision 2007 IEEE 11TH INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOLS 1-6 Saxena, A., Sun, M., Ng, A. Y. 2007: 3020-3027
  • Probabilistic Mobile Manipulation in Dynamic Environments, with Application to Opening Doors 20TH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE Petrovskaya, A., Ng, A. Y. 2007: 2178-2184
  • Depth Estimation using Monocular and Stereo Cues 20TH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE Saxena, A., Schulte, J., Ng, A. Y. 2007: 2197-2203
  • Peripheral-Foveal Vision for Real-time Object Recognition and Tracking in Video 20TH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE Gould, S., Arfvidsson, J., Kaehler, A., Sapp, B., Messner, M., Bradski, G., Baumstarck, P., Chung, S., Ng, A. Y. 2007: 2115-2121
  • Effects of polyether-polyamide block copolymer coating on performance and fouling of reverse osmosis membranes JOURNAL OF MEMBRANE SCIENCE Louie, J. S., Pinnau, I., Ciobanu, I., Ishida, K. P., Ng, A., Reinhard, M. 2006; 280 (1-2): 762-770
  • Learning factor graphs in polynomial time and sample complexity JOURNAL OF MACHINE LEARNING RESEARCH Abbeel, P., Koller, D., Ng, A. Y. 2006; 7: 1743-1788
  • Quadruped robot obstacle negotiation via reinforcement learning 2006 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), VOLS 1-10 Lee, H., Shen, Y., Yu, C., Singh, G., Ng, A. Y. 2006: 3003-3010
  • A Dynamic Bayesian Network Model for Autonomous 3D Reconstruction from a Single Indoor Image in CVPR Delage, E., Lee, H., Ng, Andrew, Y. 2006
  • On Local Rewards and the Scalability of Distributed Reinforcement Learning n NIPS Bagnell, J., Andrew, Ng, Andrew, Y. 2006; 18
  • Learning Depth from Single Monocular Images in NIPS Saxena, A., Chung, S. 2006; 18
  • From Uncertainty to Belief: Inferring the Specification Within in OSDI Kremenek, T., Twohey, P., Back, G., Ng, Andrew, Y., Engler, D. 2006
  • Transfer learning for text classification in NIPS Do, C., Ng, Andrew, Y. 2006; 18
  • Solving the problem of cascading errors: Approximate Bayesian inference for linguistic annotation pipelines in EMNLP Finkel, J., Manning, C., Ng, Andrew, Y. 2006
  • groupTime: Preference-Based Group Scheduling in CHI Brzozowski, M., Carattini, K., Klemmer, Scott, R., Mihelich, P., Hu, J., Ng, Andrew, Y. 2006
  • Efficient L1 Regularized Logistic Regression in AAAI Lee, S., Lee, H., Abbeel, P., Ng, Andrew, Y. 2006
  • Transfer Learning by Constructing Informative Priors in ICML Raina, R., Ng, Andrew, Y., Koller, D. 2006
  • Using Inaccurate Models in Reinforcement Learning in ICML Abbeel, P., Quigley, M., Ng, Andrew, Y. 2006
  • Learning Vehicular Dynamics, with Application to Modeling Helicopters in NIPS Abbeel, P., Ganapathi, V., Ng, Andrew, Y. 2006; 18
  • Fast Gaussian Process Regression using KD-trees in NIPS Shen, Y., Ng, Andrew, Y., Seeger, M. 2006; 18
  • Contextual search and name disambiguation in email using graphs in ACM SIGIR Minkov, E., Cohen, W., Ng, Andrew, Y. 2006
  • Have we met? MDP Based Speaker ID for Robot Dialogue INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5 Krsmanovic, F., Spencer, C., Jurafsky, D., Ng, A. Y. 2006: 461-464
  • Semantic Taxonomy Induction from Heterogenous Evidence COLING/ACL 2006, VOLS 1 AND 2, PROCEEDINGS OF THE CONFERENCE Snow, R., Jurafsky, D., Ng, A. Y. 2006: 801-808
  • Bayesian estimation for autonomous object manipulation based on tactile sensors 2006 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), VOLS 1-10 Petrovskaya, A., Khatib, O., Thrun, S., Ng, A. Y. 2006: 707-714
  • Report from the Rockefellar Foundation Sponsored International Workshop on reducing mortality and improving quality of life in long-term survivors of Hodgkin's disease: July 9-16, 2003, Bellagio, Italy EUROPEAN JOURNAL OF HAEMATOLOGY Mauch, P., Ng, A., Aleman, B., Carde, P., Constine, L., Diehl, V., Dinshaw, K., Gospodarowicz, M., Hancock, S., Hodgson, D., Hoppe, R., Liang, R., Loeffler, M., Specht, L., Travis, L. B., Wirth, A., Yahalom, J. 2005; 75: 68-76

    Abstract

    A workshop, sponsored by the Rockefellar Foundation, was held between 9 to 16 July, 2003 to devise strategies to reduce mortality and improve quality of life of long-term survivors of Hodgkin's disease. Participants were selected for their clinical and research background on late effects after Hodgkin's disease therapy. Experts from both developed and developing nations were represented in the workshop, and efforts were made to ensure that the proposed strategies would be globally applicable whenever possible. The types of late complications, magnitude of the problem, contributing risk factors, methodology to assess the risk, and challenges faced by developing countries were presented. The main areas of late effects of Hodgkin's disease discussed were as follows: second malignancy, cardiac disease, infection, pulmonary dysfunction, endocrine abnormalities, and quality of life. This report summarizes the findings of the workshop, recommendations, and proposed research priorities in each of the above areas.

    View details for Web of Science ID 000229591400012

    View details for PubMedID 16007872

  • Discriminative Learning of Markov Random Fields for Segmentation of 3D Range Data in CVPR Anguelov, D., Taskar, B., Chatalbashev, V., Koller, D., Gupta, D., Heitz, G. 2005
  • Robust Textual Inference via Graph Matching in EMNLP Haghighi, A., Ng, Andrew, Y., Manning, C. 2005
  • Online bounds for Bayesian algorithms in NIPS Kakade, S., Ng, Andrew, Y. 2005; 17
  • Learning Syntactic Patterns for Automatic Hypernym Discovery in NIPS Snow, R., Jurafsky, D., Ng, Andrew, Y. 2005; 17
  • Discriminative Training of Kalman Filters Abbeel, P., Coates, A., Montemerlo, M., Ng, Andrew, Y., Thrun, S. 2005
  • Robust textual inference via learning and abductive reasoning in AAAI Raina, R., Ng, Andrew, Y., Manning, C. 2005
  • Learning first order Markov models for control in NIPS Abbeel, P., Ng, Andrew, Y. 2005; 17
  • High-Speed Obstacle Avoidance using Monocular Vision and Reinforcement Learning in ICML Michels, J., Saxena, A., Ng, Andrew, Y. 2005
  • Learning factor graphs in polynomial time & sample complexity Abbeel, P., Koller, D., Ng, Andrew, Y. 2005
  • Stable adaptive control with online learning in NIPS Ng, Andrew, Y., Kim, H., Jin 2005
  • Exploration and apprenticeship learning in reinforcement learning ICML Abbeel, P., Ng, Andrew, Y. 2005
  • Spam Deobfuscation using a Hidden Markov Model Lee, H., Ng, Andrew, Y. 2005
  • In silico genetics: Identification of a functional element regulating H2-E alpha gene expression SCIENCE Liao, G. C., Wang, J. M., Guo, J. S., Allard, J., Cheng, J., Ng, A., Shafer, S., Puech, A., McPherson, J. D., Foernzler, D., Peltz, G., Usuka, J. 2004; 306 (5696): 690-695

    Abstract

    Computational tools can markedly accelerate the rate at which murine genetic models can be analyzed. We developed a computational method for mapping phenotypic traits that vary among inbred strains onto haplotypic blocks. This method correctly predicted the genetic basis for strain-specific differences in several biologically important traits. It was also used to identify an allele-specific functional genomic element regulating H2-Ealpha gene expression. This functional element, which contained the binding sites for YY1 and a second transcription factor that is probably serum response factor, is located within the first intron of the H2-Ealpha gene. This computational method will greatly improve our ability to identify the genetic basis for a variety of phenotypic traits, ranging from qualitative trait information to quantitative gene expression data, which vary among inbred mouse strains.

    View details for DOI 10.1126/science.1100636

    View details for Web of Science ID 000224756700053

    View details for PubMedID 15499019

  • Simultaneous localization and mapping with sparse extended information filters Thrun, S., Liu, Y. F., Koller, D., Ng, A. Y., Ghahramani, Z., Durrant-Whyte, H. SAGE PUBLICATIONS LTD. 2004: 693-716
  • Inverted Autonomous Helicopter Flight Via Reinforcement Learning in International Symposium on Experimental Robotics Ng, Andrew, Y., Coates, A., Diel, M., Ganapathi, V., Schulte, J., Tse, B. 2004
  • Apprenticeship Learning Via Inverse Reinforcement Learning in ICML Abbeel, P., Ng, Andrew, Y. 2004
  • Policy search by dynamic programming in NIPS Bagnell, J., Andrew, Kakade, S., Ng, Andrew, Y., Schneider, J. 2004
  • Classification with Hybrid Generative/Discriminative Models in NIPS Raina, R., Shen, Y., Ng, Andrew, Y., McCallum, A. 2004; 16
  • Online Learning of Pseudo-Metrics in ICML Shalev-Shwartz, S., Singer, Y., Ng, Andrew, Y. 2004
  • Feature selection, L1 vs. L2 regularization, and rotational invariance in ICML Ng, Andrew, Y. 2004
  • Latent Dirichlet allocation Blei, D. M., Ng, A. Y., Jordan, M. I. MICROTOME PUBL. 2003: 993-1022
  • Distance metric learning, with application to clustering with side-information in NIPS Xing, E., Ng, Andrew, Y., Jordan, M. 2003; 15
  • On Spectral Clustering: Analysis and an algorithm in NIPS Ng, Andrew, Y., Jordan, M. 2002; 14
  • On Discriminative vs. Generative Classifiers: A comparison of logistic regression and Naive Bayes in NIPS Ng, Andrew, Y., Jordan, M. 2002; 14
  • Data-Intensive Question Answering in TREC Brill, E., Lin, J., Banko, M., Dumais, S. 2001; 10
  • Convergence rates of the Voting Gibbs classifier, with application to Bayesian feature selection in ICML Ng, Andrew, Y., Jordan, M. 2001
  • Stable algorithms for link analysis in ACM SIGIR Ng, Andrew, Y., Zheng, Alice, X., Jordan, M. 2001
  • Link analysis, eigenvectors, and stability in IJCAI Ng, Andrew, Y., Zheng, Alice, X., Jordan, M. 2001
  • Approximate inference algorithms for two-layer Bayesian networks in NIPS Ng, Andrew, Y., Jordan, M. 2000; 12
  • Approximate planning in large POMDPs via reusable trajectories in NIPS Kearns, M., Mansour, Y., Ng, Andrew, Y. 2000; 12
  • Policy search via density estimation in NIPS Ng, Andrew, Y., Parr, R., Koller, D. 2000; 12
  • Algorithms for inverse reinforcement learning in ICML Ng, Andrew, Y., Russell, S. 2000
  • PEGASUS: A policy search method for large MDPs and POMDPs Ng, Andrew, Y., Jordan, M. 2000
  • Policy invariance under reward transformations: Theory and application to reward shaping in ICML Ng, Andrew, Y., Harada, D., Russell, S. 1999
  • A sparse sampling algorithm for near-optimal planning in large Markov decision processes in IJCAI Kearns, M., Mansour, Y., Ng, Andrew, Y. 1999
  • Improving Text Classification by Shrinkage in a Hierarchy of Classes in ICML McCallum, A., Rosenfeld, R., Mitchell, T., Ng, Andrew, Y. 1998
  • Applying Online-search to Reinforcement Learning in AAAI Davies, S., Ng, Andrew, Y., Moore, A. 1998
  • On Feature Selection: Learning with Exponentially many Irrelevant Features as Training Examples in ICML Ng, Andrew, Y. 1998
  • Preventing “Overfitting” of Cross-Validation data in ICML Ng, Andrew, Y. 1997
  • An Information-Theoretic Analysis of Hard and Soft Assignment Methods for Clustering Kearns, M., Mansour, Y., Ng, Andrew, Y. 1997
  • An Experimental and Theoretical Comparison of Model Selection Methods in Machine Learning Kearns, M., Mansour, Y., Ng, Andrew, Y., Ron, D. 1997; 1 (27): 7-50

Stanford Medicine Resources: