Software Engineering Radio - the podcast for professional software developers cover image

Episode 391: Jeremy Howard on Deep Learning and fast.ai

Software Engineering Radio - the podcast for professional software developers

00:00

Are the Current Weights Good or Bad?

The fifth in the training process to say, are the current weights good or bad? When you feed in with ay a particular image of a dog or a cat, and it actually says the probability is high that it's a dog, then that oud be bad. And so there's literally a line of code in fasti that says, weights minus equals weight stock radiance times learning rate. So that's the actual thing that up dates the weights until you kind of get to some of the later lessons in fastot a i.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app