I am a fifth year Computer Science and Engineering Ph.D. student at the University of Washington, where I work with Rajesh Rao. I received my B. Eng. in Computer Engineering from the University of Victoria in British Columbia, Canada.
Thanks to funding from NSERC, I am able to pursue my interests in developing flexible and robust artificial learning agents. Specifically, I am interested in developing new theory and techniques for artificial intelligence, control, and machine learning that rely on fewer assumptions and are capable of learning and generalizing across multiple tasks and domains. I am also interested in neuroscience and cognitive science, and using ideas from human learning to improve artificial learning.
I am currently exploring and developing probabilistic techniques for artificial learning through imitation and goal-inference. Nonparametric Bayesian modeling is a powerful and flexible tool for expressing rich statistical models in a natural fashion and may provide new insights into imitation learning and goal-inference. Its flexibility has also proven useful for developing novel cognitive science models. I recently presented a paper (below) at the annual meeting of the cognitive science society (CogSci 2011) where we used Gaussian processes to model gaze-following in humans.
In the summer of 2010, I did an internship at Intel Labs in Seattle, working with Dieter Fox on Human Robot Interaction. Over the winter quarter (Jan-Mar 2011), I lived in San Francisco while collaborating with Tom Griffith's Computational Cognitive Science Lab at Berkeley. This collaboration resulted in a paper at NIPS 2011 on the inference of reference frames of objects by both humans and a computational model we created.
From April-September 2011, I was at MIT in Cambridge, MA, working with David Wingate and jointly visiting the labs of Leslie Kaelbling and Josh Tenenbaum. My work there involved investigations into a more natural and flexible model of planning within a learned, object-oriented framework, as well as research into improving the generality and robustness of inference techniques for probabilistic models.
Here is a link to my CV.
Projects and PublicationsPlanning and Decision Making
Yanping Huang, Abram L. Friesen, Timothy D. Hanks, Michael N. Shadlen, and Rajesh P. N. Rao (2012). How prior probability influences decision making: a unifying probabilistic model. In Proceedings of the 26th Annual Conference on Neural Information Processing Systems. Lake Tahoe, Nevada. December, 2012. (pdf)
Inferring Object Reference Frames
Joseph L. Austerweil, Abram L. Friesen, and Thomas L. Griffiths (2011). An ideal observer model for identifying the reference frame of objects. In Proceedings of the 25th Annual Conference on Neural Information Processing Systems. Granada, Spain. December, 2011. (pdf)
Abram L. Friesen and Rajesh P. N. Rao (2011). Gaze Following as Goal Inference: A Bayesian Model. In L. Carlson, C. Hölscher, & T. Shipley (Eds.), Proceedings of the 33rd Annual Conference of the Cognitive Science Society. Boston, MA: Cognitive Science Society. July, 2011. (pdf)
Abram L. Friesen and Rajesh P. N. Rao (2010). Imitation Learning with Hierarchical Actions. In Proceedings of the International Conference on Learning and Development (ICDL), Ann Arbor, MI, USA. August, 2010. (pdf)
Query Progress Estimation
Kristi Morton, Abram Friesen, Magdalena Balazinska, and Dan Grossman (2010). Estimating the Progress of MapReduce Pipelines. In Proceedings of the 26th IEEE International Conference on Data Engineering (ICDE), Long Beach, CA, USA. March, 2010. (pdf)