Practical Use for AI and Machine Learning in Science

Universe Today Podcast - A podcast by Fraser Cain

AI is practically everywhere right now. But what practical use does it have in science? How can machine learning and large language models help in Astronomy and Cosmology? What can they look like and what use can we get out of them? šŸŸ£ Guest: Dr Mike Smith https://www.mjjsmith.com/ šŸ‘‰ AstroPT on GitHub: https://github.com/Smith42/astroPT šŸ‘‰ AstroPT Discord: discord.gg/MNEVegvfJq šŸ“œ AstroPT: Scaling Large Observation Models for Astronomy https://arxiv.org/abs/2405.14930 šŸ¦„ Support us on Patreon: https://patreon.com/universetoday šŸ“š Suggest books in the book club: https://www.goodreads.com/group/show/1198440-universe-today-book-club 00:00 Intro 01:40 AI in modern science 05:33 Astronomy data for AstroPT 10:50 How does it work 17:15 How people can use AstroPT 19:58 Training data 22:45 Better understanding of Physics 28:58 What's next 38:51 The perfect data to feed AI 43:55 Current obsessions 47:40 Final thoughts šŸ“ŗ VIDEO VERSION https://youtu.be/SexDIF__8l4 šŸ“° EMAIL NEWSLETTER Read by 60,000 people every Friday. Written by Fraser. No ads. Subscribe. It's FREE: https://universetoday.com/newsletter šŸŽ§ PODCASTS Universe Today: https://universetoday.fireside.fm/ Astronomy Cast: http://www.astronomycast.com/ šŸ¤³ OTHER SOCIAL MEDIA Twitter: https://twitter.com/fcain Twitter: https://twitter.com/universetoday Facebook: https://facebook.com/universetoday Instagram: https://instagram.com/universetoday šŸ“© CONTACT FRASER [email protected] āš–ļø LICENSE Creative Commons Attribution 4.0 International (CC BY 4.0)Support Universe Today Podcast