AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
4min chapter
Probabilistic Numeric CNNs with Roberto Bondesan - #482
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
The Convolutional Layer on a Continuous Function
The convolutional layer is defined in terms of a linear pid, a partial differential equation. This restricts the forms of differential equations that you can put in your newernetwork. And it turns out that for certain choices,. indeed, of layers, we can do computations analytically. So we can actually propagate this function of forms, wi nover cod analytically. That's pretty cool.
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