Communications of the ACM
Data Scientists Face Off in LSST Machine-Learning Competition
In an international machine learning challenge hosted on the Kaggle.com platform, participants were provided a simulated dataset of 3 million objects and asked to identify which of 15 classifications was the best fit for each object.
Credit: LSST Collaboration
An international machine learning challenge hosted on the Kaggle.com platform provided a simulated dataset of 3 million objects and asked participants to identify which of 15 classifications was the best fit for each object.
The Photometric LSST Astronomical Time-Series Classification Challenge (PLAsTiCC) was founded via a collaboration between two science groups working on the Large Synoptic Survey Telescope (LSST) project.
The University of California, Berkeley's Kyle Boone won a $12,000 prize for his first-place finish, and also participated in a second phase of the competition that was more open-ended and is driving toward more applicable solutions in categorizing the objects that LSST will see.
Boone hopes to apply his programming work for the LSST competition to his work at the Lawrence Berkeley National Laboratory, and he aims to prepare a scientific paper based on the machine learning code he wrote for the contest.
From Symmetry Magazine
View Full Article
Abstracts Copyright © 2019 SmithBucklin, Washington, DC, USA
No entries found