AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
4min chapter
François Chollet: Keras and Measures of Intelligence
The Gradient: Perspectives on AI
The Design Principle of Progression in Deep Learning
The idea that I showed in the software I should make things simple, but you should not be facing a cliff at some point where you're trying to customize things further. So you should make sure you have this gradual smooth drop-off to a lower layer of implementation. In general, there's no abstract answer to this question. Your abstractions have to be designed after the mental models of the main experts so it really depends. But in deep learning, the big steps are something that are going to be like, you prepare your data and you preprocessYour model, then potentially you might define it with hypervibrators if you want to then have a banter sweep. And eventually, you
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