AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
4min chapter
Towards stability and robustness
Practical AI: Machine Learning, Data Science, LLM
How to Build a Distribution Detection Model?
The two most citical elements, i thing, are well, straightforward, but not easy to build out of distribution detection. Then you have the other part, which is confidence or uncertainty. I like the term confidence estimation because it's mose straightforward atd not the negative. And going back to the mission critical pall of elements, now i can treshold something and make sure that if the confidence is below the threasure pass tate a human rigt. Once again, that's change log dot com slash plus plus. Change log plus pus.
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