A Machine That Can Predict Exoplanets

Exciting new research from the Cool Worlds Lab has delved into the use of machine learning and artificial neural networks for astronomy. In new work from David Kipping & Chris Lam here at Columbia, we've shown how a machine can predict the presence of extra planets in known planetary systems using just a few pieces of information about the system. Chris Lam gives a neural network 101 and explains our implementation works.::More about this Video::► Kipping & Lam 2016, "Transit Clairvoyance: Enhancing TESS follow-up using artificial neural networks": https://arxiv.org/abs/1611.04904► Tamayo et al. (2016), "A Machine Learns to Predict the Stability of Tightly Packed Planetary Systems": https://arxiv.org/abs/1610.05359► Graff et al. (2013), "SKYNET: an efficient and robust neural network training tool for machine learning in astronomy": https://arxiv.org/abs/1309.0790► Waldmann (2016), "Dreaming of atmospheres": https://arxiv.org/abs/1511.08339► Outro music by Taylor Davis: https://www.youtube.com/watch?v=dl9kI1yQKZk::Playlists For Channel::Latest Cool Worlds Videos ► http://bit.ly/NewCoolWorldsCool Worlds Research ► http://bit.ly/CoolWorldsResearchGuest Videos ► http://bit.ly/CoolWorldsGuestsQ&A Videos ►http://bit.ly/CoolWorldsQAScience of TV/Film ► http://bit.ly/ScienceMovies::Follow us::SUBSCRIBE to the channel http://bit.ly/CoolWorldsSubscribeCool Worlds Lab http://coolworlds.astro.columbia.eduTwitter https://twitter.com/david_kippingInstagram https://www.instagram.com/cool.worldsTHANKS FOR WATCHING!! Learn more about your ad choices. Visit megaphone.fm/adchoices