AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
4min chapter
Anton Teaches Packy AI | E1
"Age of Miracles"
Is Attention a Multi-Head Mechanism?
So first we have this thing called a multi-head attention mechanism. Attention weights the input appropriately in order to make a weighted prediction instead of a flat equally distributed prediction. Now, then it has this other thing where it says add and norm. So what that allows you to do here is, okay, we're getting like these values out of the attention heads, but we also want to keep what we had originally,. so that we can keep propagating that information as well.
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