How to Make Machine Learning Work in A Data-Limited System (5 of 8) (IMAGE)
Caption
A photograph of crumpled mylar, the corresponding laser scanned heightmap, and the resulting curvature map all overlayed. We show the data-collection pipeline imposed on a single image. In the upper right, we show a photograph of raw data. This fades into the heightmap that the laser scans (in the bottom, middle) and into the mean curvature map computed from the laser scan in the upper left. This material relates to a paper that appeared in the April 26th, 2019, issue of Science Advances, published by AAAS. The paper, by J. Hoffmann at Harvard University in Cambridge, MA, and colleagues was titled, "Machine learning in a data-limited regime: Augmenting experiments with synthetic data uncovers order in crumpled sheets."
Credit
Jordan Hoffmann, Shruti Mishra, and Lisa Lee
Usage Restrictions
Please cite the owner of the material when publishing. This material may be freely used by reporters as part of news coverage, with proper attribution. Non-reporters must contact <i>Science</i> for permission.
License
Licensed content