Chris Garry recently graduated from the University of Massachusetts Amherst with a BS in computer engineering. He is passionate about solving problems that lie at the intersection of robotics, the biological sciences, and artificial intelligence, and strongly believes that interdisciplinary practice is essential to the future of truly intelligent systems. As an undergraduate, Chris worked in both academic and government research labs on problems in cyber security, robotics, intelligent systems, neurobiology, and computer vision. Aside from his academic interests, Chris enjoys programming, playing piano, and keeping up with technology.
Project: Clustering Time Series Data
It is often useful to be able to compare two time series in order to determine how similar they are. This is a common task in speech analysis where two speech signals are being compared, or in gesture recognition when the task is to classify movement. This project will explore comparing time series data to generate a similarity metric by which a set of time series will be clustered. Specifically, this algorithm will be evaluated by clustering words based on their usage. This will help identify useful trends such as words that are commonly used together.
Here are two clusters computed from a set of 100 words.
Favorite Outer Totalistic r=1, k=2 2D Cellular Automaton