Programming Throwdown cover image

The Art of Vacations

Programming Throwdown

00:00

Computer Vision

The idea is that when gogle trains this model on everything, it builds some understanding about how to tell what isn'tor isn't in a picture. And so almost any image processing thing you're going to train is going to take advantage of that, right? So imagine, for example, if you had just random noise, and the goal was to predict,. like, the number of white pixtles, like eve, a random bindary mage such as generated with random numbers... That would be really hard to transfer learn because there's no symmetry or anything real there.

Play episode from 19:53
Transcript

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