AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
2min chapter
Anton Teaches Packy AI | E1
"Age of Miracles"
The Position Encoding in a Recurrent Model
In the GPT-3 playground screen, the regular text that I type at the top before you see all the green highlighted stuff below is the input. That's the input that we're talking about here. And that gets turned into numbers, a vector of numbers. And then the next thing that happens here is the positional encoding. This is actually a really important thing. In a recurrent model like an LSTM, you don't need the position encoding. The position encoding is like implicit because if you're on the nth step, you know you're talking about the nth position. Here we've got the whole text at once.
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