A five-year, $1.5-million award from the Simons Foundation will enable Duke University professor Ingrid Daubechies to expand her collaborative research involving mathematics and electrical engineering.
Daubechies will use the award to build machine learning tools that offer new ways to mine data.
Some researchers have argued new approaches are needed in order to keep up with the deluge of data. "The large volumes of data that are being generated left and right definitely present a serious challenge," Daubechies says.
Daubechies has been focusing on training computers to churn through electrocardiogram tracings, high-resolution scans of fossils, paintings, and other complex digital data and work things out automatically.
One new technique Daubechies is working on involves comparing three-dimensional (3D) shapes, which relies on computational geometry to make the process less time-consuming and subjective for computers. For the past seven years, Daubechies has been working with fossil experts to analyze 3D images of bones and teeth.
From Duke Today
View Full Article
Abstracts Copyright © 2016 Information Inc., Bethesda, Maryland, USA
No entries found