AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
2min chapter
Deep Unsupervised Learning for Climate Informatics with Claire Monteleoni - #497
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
How to Interpret the Geodesics of the Posterior Distribution
The trade off is between complicating your prior so much that you're basically overfitting, versus getting really good fidelity maps at the fine resolution. So bryan looked at two images at different times in one domain, map them to latent space. He decided to use glow for the alizing flow, which had shown great success on celebrity faces,. And wanted to see if we could get some good fidelity around weather.
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode