The idea of swapping is to make neurons movable and trainable. When you first try module edition without swapping, the networks looks a little bit like 3D DNA, the double helix, but projected to 2D. So that's why we end up using swapping,. But potentially one could also imagine try, make those embeddings trainable. And then we can get more into like understanding it as well.

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

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

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