I was surprised by how clever neural networks can be. When I saw the connectivity graph, so for binary classification, what really matters is like the difference of the logistic classes. So an efficient strategy for neural classifiers is to simply set class A to always have zero logits while only learning the logic function for another class B. Yeah, this is a very interesting observation. At first, it's messy, everything fully connected and then in the middle in the middle state, there are like the sparse network and also symmetric for the two classes. And finally, the network realizes that it only needs to predict the logist for one class while pruning away totally for the other class.

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