Training a Machine to Watch Soccer
08-25-17
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
How Friction Evolves During an Earthquake
08-15-17
Professor Ares Rosakis, and colleagues including Professor Nadia Lapusta and Research Scientist Vito Rubino, are studying the way friction changes along a fault during a seismic event by simulating quakes in a lab. "Our unique facility … allows us for the first time to study friction point-wise and without having to assume that sliding occurs uniformly, as is done in classical friction studies," Rosakis explains. Professor Lapusta adds, “some numerical models of earthquake rupture … have used friction laws with slip-velocity dependence… It is gratifying to see those formulations validated by the spontaneous mini-earthquake ruptures in our study. " [Caltech story]
Tags:
research highlights
GALCIT
MCE
Ares Rosakis
Nadia Lapusta
Vito Rubino
Deep Learning Networks and Sensorimotor Control
08-08-17
Professor John Doyle and colleagues are among only nineteen groups in the United States to receive National Science Foundation (NSF) funding to conduct innovative research focused on neural and cognitive systems. They aim is to integrate the capabilities of deep learning networks into a biologically inspired architecture for sensorimotor control that can be used to design more robust platforms for complex engineered systems. [NSF release]
Tags:
EE
research highlights
CMS
John Doyle
Neural Networks Model Audience Reactions to Movies
07-21-17
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
Reflective Nanostructures
07-13-17
Andrei Faraon, Assistant Professor of Applied Physics and Materials Science, and colleagues have discovered how to use computer-chip manufacturing technologies to create the kind of reflective materials that make safety vests, running shoes, and road signs appear shiny in the dark. The new technology uses surfaces covered by a metamaterial consisting of millions of silicon pillars, each only a few hundred nanometers tall. By adjusting the size of the pillars and the spacing between them, Faraon can manipulate how the surface reflects, refracts, or transmits light. [Caltech story]
Tags:
APhMS
research highlights
Andrei Faraon