The SETI Institute is inviting all citizen data scientists to join us as collaborators in our mission to find intelligent radio signals from beyond our solar system by issuing a worldwide, public code challenge using the latest developments available in machine- and deep-learning. We are looking for signal classification algorithms and models that can accurately identify the various types of radio signals we observe each night.
To help in this adventure (and for the hackathon), IBM has donated the PowerAI platform and the Watson Data Science Experience environment for both the search for alien signals and to crunch the numbers needed to devise new algorithms in the code challenge.
Jon Richards, SETI Operator and an electrical engineer, explains the Allen Telescope Array and demonstrates the signal data the ATA deals with. See #2.
Amateur Astronomer and Software Engineer/Data Scientist (and hackathon competitor) Kyle Buckingham talks about what the challenge provided him - namely, exposure to analytics methods and data science tools. See #3.
Dan Werthimer is co-founder and chief scientist of the SETI@home project and he details the importance of new and enhanced algorithms to improve the signal analysis part of the effort. See #4.
Physicist and Director of Research at SETI, Gerry Harp takes the participants down into some of the code used currently to tease signals out of noisy data. See #5.
The teams describe their projects and the difficulties they faced. Systems engineers, software engineers, physicists - a range of data scientists come together to attempt to construct a classifier algorithm, one that would recognize a signal in the interstellar noise. See #3.