AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
4min chapter
Jeff Hawkins: Thousand Brains Theory of Intelligence
Lex Fridman Podcast
The Ont Printers Dilemma
In the brain, if i have like ten thousand neurons, what you would see is maybe two % of hem active at a time. It's always like that for any set of sensory imputs - it doesn't matterf anything. If you enforce sparseness throughout these convolutional le networks, in both the whichof runs are active and the connections between em hat you get some very desirable properties. They're much more robust, and they're not easy to fool. So we've already shown some of those results. Just literally, in january or february last month, we did our first deep-learning experiment with an adversarial example. We know why it's important
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