AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
2min chapter
Learning Long-Time Dependencies with RNNs w/ Konstantin Rusch - #484
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
How Long Do You Let the Aren End Model Learn?
We tried elst ms at least for 600 hundreds, or for 60 thousand a learning steps, and it did not converge at all. And also, the other important architectures like this exponenta arenn, which is basically some kind of unitary arenn didn't work so well. So we trit this task from its pasically human action recognition. It's basically on a smart phone with the censors a measured six different activities,. The idea is that you have sometimes serious measured from your censors over time to classify what people are doing.
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