When we think about the model, the model has two components. The architecture itself is to say, okay, you give us this vector, we're gonna transform in the following way. And then there's the parameters of that architecture, which are usually called the weights. These numbers go into that architecture and they tell that architecture how to behave. They literally weight different parts of it. Training is the process of changing those weights, literally the numbers,. Those potentially billions of numbers, changing them so that they encode information for when you run an input through the model You get an output that is sensible.

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