Email: first initial followed by last name at acm dot org
I'm currently VP of Data Science at DataSeer, a JV between Arundo Analytics & Worley, working on on machine learning + computer vision for industrial engineering. Previously, I was Lead Data Scientist at Arundo Analytics from 2018 to 2020, working on industrial ML, and Director of Data Science at Aura Financial from 2014 to 2018, building systems to optimize credit and operational risk. From 2011 to 2013, I was a Research Scientist at Bosch Research and Technology Center in Palo Alto, CA. Prior to that, I spent some time at the University of Edinburgh in 2009, working with Sethu Vijayakumar, and at the University of British Columbia from 2010 to 2011, as an NSERC postdoctoral fellow, working with Nando de Freitas, Kevin Murphy, and Jim Little. I received my PhD in Computer Science from the University of Southern California in 2009, where I was advised by Stefan Schaal, and a BASc in Computer Engineering from the University of Waterloo in 2003.
- W.-L. Lu, J. Ting, K. Murphy, and J. Little. Learning to Track and Identify Players from Broadcast Sports Videos, IEEE Transactions on Pattern Analysis and Machine Intelligence 35(7): 1704-1716. [paper]
- W.-L. Lu, J. Ting, K. Murphy, and J. Little. Identifying Players in Broadcast Sports Videos using Conditional Random Fields, IEEE Computer Vision and Pattern Recognition (CVPR). [paper]
- L. Bazzani, N. de Freitas, H. Larochelle, V. Murino, and J. Ting Learning Attentional Policies for Tracking and Recognition in Video with Deep Networks, International Conference on Machine Learning (ICML).
- J. Ting, A. D'Souza, and S. Schaal. Bayesian Robot System Identification with Input and Output Noise, Neural Networks, 24(1): 99-108. [preprint]
- H. P. Saal, J. Ting, and S. Vijayakumar. Active Sequential Learning with Tactile Feedback, International Conference on Artificial Intelligence and Statistics (AISTATS), JMLR: W&CP 9: 677-684. [pdf]
- H. P. Saal, J. Ting, and S. Vijayakumar. Active Estimation of Object Dynamics Parameters with Tactile Sensors, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). [pdf]
- B. Chen, J. Ting, B. M. Marlin, and N. de Freitas. Deep Learning of Invariant Spatio-temporal Features from Video, NIPS Workshop on Deep Learning and Unsupervised Feature Learning, Oral talk.
- L. Bazzani, N. de Freitas, and J. Ting. Learning Attentional Mechanisms for Simultaneous Object Tracking and Recognition with Deep Networks, NIPS Workshop on Deep Learning and Unsupervised Feature Learning.
- J. Ting, A. D'Souza, S. Vijayakumar, and S. Schaal. Efficient Learning and Feature Selection in High-Dimensional Regression, Neural Computation, 22(4): 831-886. [preprint]
- J. Ting, S. Vijayakumar, and S. Schaal. Locally Weighted Regression for Control, Encyclopedia of Machine Learning (eds: Sammut, C. and Webb, G. I.), 613-624, Springer. [preprint]
- H. P. Saal, J. Ting, and S. Vijayakumar. Active Filtering for Robotic Tactile Learning, NIPS Workshop on Adaptive Sensing, Active Learning and Experimental Design: Theory, Methods and Applications, Poster.
- J. Ting, Bayesian Methods for Autonomous Learning Systems, Phd Thesis, Department of Computer Science, University of Southern California. [pdf]
- J. Ting, M. Kalakrishnan, S. Vijayakumar, and S. Schaal. Bayesian Kernel Shaping for Control, Advances in Neural Processing Systems (NIPS). [pdf] [appendix]
- J. Ting, A. D'Souza, S. Vijayakumar, and S. Schaal. A Bayesian Approach to Empirical Local Linearization for Robotics, International Conference on Robotics and Automation (ICRA). [pdf] [slides]
- J. Ting, A. D'Souza, K. Yamamoto, T. Yoshioka, D. Hoffman, S. Kakei, L. Sergio, J. Kalaska, M. Kawato, P. Strick, and S. Schaal. Variational Bayesian Least Squares: An Application to Brain-Machine Interface Data, Neural Networks: Special Issue on Neuroinformatics, 21(8), 1112-1131. [pdf]
- J. Ting, and S. Schaal. Local Kernel Shaping for Function Approximation, Learning Workshop, Snowbird, April 2008, Poster.
- J. Ting, E. Theodorou, and S. Schaal. Learning an Outlier-Robust Kalman Filter, European Conference on Machine Learning (ECML). [pdf]
- J. Ting, A. D'Souza, and S. Schaal. Automatic Outlier Detection: A Bayesian Approach, International Conference on Robotics and Automation (ICRA). [pdf] [slides]
- J. Ting, E. Theodorou, and S. Schaal. A Kalman filter for Robust Outlier Detection, IEEE International Conference on Intelligent Robotics Systems (IROS). [pdf] [slides]
- J. Ting, A. D'Souza, K. Yamamoto, T. Yoshioka, D. Hoffman, S. Kakei, L. Sergio, J. Kalaska, M. Kawato, P. Strick, and S. Schaal. Using Variational Bayesian Least Squares for EMG Data Prediction from M1 and Premotor Cortex Neural Firing, Abstracts of the 37th Meeting of the Society of Neuroscience (SFN). [poster]
- J. Ting and S. Schaal. Bayesian Nonparametric Regression with Local Models, NIPS Workshop on Robotic Challenges for Machine Learning, Poster.
- J. Ting, A. D'Souza, and S. Schaal. Bayesian Regression with Input Noise for High Dimensional Data, International Conference on Machine Learning (ICML). [pdf] [slides]
- J. Ting, M. Mistry, J. Peters, S. Schaal, and J. Nakanishi. A Bayesian Approach to Nonlinear Parameter Identification for Rigid Body Dynamics, Robotics: Science and Systems (RSS). [pdf]
- J. Ting, J., A. D'Souza, A., K. Yamamoto, T. Yoshioka, D. Hoffman, S. Kakei, L. Sergio, J. Kalaska, M. Kawato, P. Strick, and S. Schaal. Predicting EMG Data from M1 Neurons with Variational Bayesian Least Squares, Advances in Neural Information Processing Systems (NIPS). [pdf]
- J. Ting, A. D'Souza, and S. Schaal. Predicting EMG Activity from Neural Firing in M1 with Bayesian Backfitting, 11th Joint Symposium of Neural Computation (JSNC).
Variational Bayesian Least Squares:
A variational Bayesian algorithm performs efficient high-dimensional linear regression, handling large numbers of irrelevant and redundant dimensions in the input data. Good references include Ting, D'Souza, Vijayakumar & Schaal (2010) in Neural Computation and Ting & al. (Neural Networks: Neuroinformatics, 2008). Older conference proceedings include Ting & al. (2005) in NIPS and D'Souza, Vijayakumar & Schaal (2004) in ICML.
Bayesian Regression with Input Noise for High Dimensional Data:
A Bayesian treatment of factor analysis in joint-space that can accurately identify parameters in a high-dimensional linear regression problem when input data is noise-contaminated. An application to nonlinear parameter identification in Rigid Body Dynamics is described in Ting, Mistry, Peters, Schaal & Nakanishi (RSS 2006). A good reference is Ting, D'Souza & Schaal in Neural Networks (2010).
Real-time outlier detection:
A weighted least squares-like approach to outlier detection, where each data sample has a weight associated with it. This model treats the weights probabilistically and learn their optimal values, avoiding modeling with heuristic error functions, sampling or tuning of open parameters (such as a threshold parameter). Details on how to perform automatic outlier detection in linear regression can be found in the paper by Ting, D'Souza & Schaal (2007) in the ICRA proceedings. We can also incorporate this approach to a Kalman filter, allowing us to do real-time automatic outlier detection on streaming data. A good reference is Ting, Theodorou & Schaal (2007) in ECML.