Ziminglu from MIT has developed a way to make neural networks more interpretable by design. His work is based on the idea of brain-inspired modular training for mechanistic interpretability. Ziminglu: "We kind of rely on the analogy to human brains, where in brains different parts of our brains are responsible for different functions" The key trick he used was embedding the network into a geometric space where you can define distances and we have a penalty proportional to the length of the connections.

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