Meet the 2017 Amazon Fellows


Four graduate students from the Computing and Mathematical Sciences (CMS) Department and one from the Electrical Engineering (EE) Department have been selected as 2017 Amazon Fellows. This fellows program is the result of a partnership between Caltech and Amazon AWS around Machine Learning and Artificial Intelligence. The EE fellow is Srikanth Tenneti who is exploring the potential of deep learning for Direction of Arrival applications, and extending Ramanujan Sums based techniques for multi-dimensional periodicity extraction. CMS graduate student Navid Azizan Ruhi is researching faster optimization algorithms for machine learning.  He is looking forward to visiting Amazon AI as a fellow and exchanging ideas with their researchers. Computer science graduate student Hoang Le is developing methods for efficient and intelligent sequential decision making in realistic systems. Florian Schaefer, whose focus is applied and computational mathematics, is researching the interface of statistical estimation and the design of fast algorithms. Control and dynamical systems graduate student Ellen Feldman, working with Professor Joel Burdick, has used part of the funding to present her research at the Society for Neuroscience annual meeting and looking forward to other future opportunities to share her research. 

Tags: EE honors CMS P. P. Vaidyanathan Babak Hassibi Joel Burdick Yisong Yue Navid Azizan Ruhi Hoang Le Ellen Feldman Florian Schaefer Srikanth Tenneti Houman Owhadi

Caltech and Disney Engineers Collaborate on Robotics


Caltech and Disney Research have entered into a joint research agreement to pioneer robotic control systems and further explore artificial intelligence technologies. Pietro Perona will work with Disney roboticist Martin Buehler to create navigation and perception software that could allow robotic characters to safely move through dense crowds and interact with people. Aaron Ames will work with Disney Research's Lanny Smoot to further explore robot autonomy and machine learning by creating objects that can self-navigate and perform stunts. Yisong Yue has been working with engineers from Disney Research on the use of machine learning to analyze the behavior of soccer players and to measure audience engagement. [Caltech story]

Tags: EE research highlights MCE CMS Pietro Perona Yisong Yue Aaron Ames

Best Poster Award At Neural Information Processing Systems Conference


CMS postdoctoral scholar Qi (Rose) Yu, working with Professor Anandkumar, and graduate student Stephan Zheng, working with Professor Yue, have won the Best Poster Presentation Award at the 2017 Neural Information Processing Systems (NIPS) Time Series Workshop. Dr. Yu works on the challenge of long-term forecasting in environments with nonlinear dynamics such as those involving climate and traffic data. She is tackling this challenge uses Tensor-Train RNN which are a novel family of neural sequence models that learn nonlinear dynamics directly using higher order moments and high-order state transition functions. [View her poster]

Tags: honors CMS Yisong Yue Animashree Anandkumar postdocs Qi (Rose) Yu Stephan Tao Zheng

AWS and Caltech Partner to Accelerate AI and Machine Learning


From autonomous robotics to state of-the-art computer vision, Caltech and Amazon have a lot in common, including the belief that pushing the boundaries of artificial intelligence (AI) and machine learning (ML) will not only disrupt industries, but it will fundamentally change the nature of scientific research. As part of this two-year renewable research collaboration, Amazon will provide both financial support, in the form of funding for graduate fellowships, and computing resources, in the form of AWS Cloud credits, to accelerate the work of faculty and students at Caltech in these areas. [AWS AI Blog]

Tags: CMS Adam Wierman Pietro Perona Joel Tropp Yisong Yue Aaron Ames Animashree Anandkumar

Training a Machine to Watch Soccer


Yisong Yue, Assistant Professor of Computing and Mathematical Sciences, and colleagues have developed an algorithm that can automatically recognize formations of teams—how they arrange themselves on the field—when analyzing player tracking data. The algorithm can also imitate players' behavior. "We're training the algorithm to understand soccer at the same level that a fan would. It's not just mindlessly watching faceless players move across a field; it's watching strikers and right midfielders and forwards arrange themselves in specific formations," says Professor Yue. [Caltech story]

Tags: research highlights CMS Yisong Yue

Neural Networks Model Audience Reactions to Movies


Yisong Yue, Assistant Professor of Computing and Mathematical Sciences, and colleagues have created a new deep-learning software capable of assessing complex audience reactions to movies using the viewer's facial expressions. "Understanding human behavior is fundamental to developing AI [artificial intelligence] systems that exhibit greater behavioral and social intelligence. For example, developing AI systems to assist in monitoring and caring for the elderly relies on being able to pick up cues from their body language. After all, people don't always explicitly say that they are unhappy or have some problem," Professor Yue says. [Caltech story]

Tags: research highlights CMS Yisong Yue

MIT Sloan Sports Analytics Conference


Graduate student, Hoang M. Le, from Professor Yisong Yue’s group was runner-up for the best paper award at the MIT Sloan Sports Analytics Conference. He was recognized for his paper, Data-Driven Ghosting using Deep Imitation Learning. [Read the paper]

Tags: honors CMS Yisong Yue Hoang Le

Realtime Camera Planning


Yisong Yue, Assistant Professor of Computing and Mathematical Sciences, is working with colleagues at Disney Research to develop machine-learning algorithms to make automated cameras more human-like.  Professor Yue's research group is generally interested in building AI systems that imitate demonstrated behavior, including laboratory animals, basketball players, humans playing video games, etc.  In this recent work with Disney Research, they are developing an automated camera system that learns how best to film sports matches by watching how human camera operators behave at particular moments. Early testing shows that its shots are far smoother than other automated cameras. [Learn more about the applications] [Learn more about the theory] [techradar story] [Sports Illustrated story]

Tags: research highlights CMS Yisong Yue

Professor Yue Receives Bloomberg Data Science Grant


Yisong Yue, Assistant Professor of Computing and Mathematical Sciences, is a recipient of the Bloomberg Data Science Research Grant Program. The program aims to support cutting-edge research in the broad field of machine learning, including specific areas such as natural language processing, information retrieval, machine-translation and deep neural networks. Professor Yue has proposed to study an alternative notion of interpretability, which he calls “dynamic interpretability”. The goal of dynamically interpretable models is to make predictions that are interpretable, rather than have the model itself be explicitly interpretable. With this alternative goal, one can circumvent much of the inherent tension between accuracy and traditional “static” interpretability, and move one step closer to interpretable production-strength models.[Bloomberg release]

Tags: honors CMS Yisong Yue

2015 Bhansali Prize Award Winners


Bryan He, a senior student advised by Yisong Yue, and William Hoza, a junior student advised by Leonard Schulman, are the recipients of the 2015 Bhansali Prize. Nicholas Schiefer, a junior student advised by Erik Winfree, won an honorable mention for the Prize. The Bhansali Prize is typically awarded to one undergraduate student for outstanding research in Computer Science in the current academic year, but due to the number of particularly high-caliber candidates in 2015, the Bhansali Prize committee determined that multiple students deserved the award.

More »

Tags: honors CMS Erik Winfree Yisong Yue Bryan He William Hoza Nicholas Schiefer Leonard Schulman