Orchestrate all the Things cover image

The next 10 years in AI: From bits to things, from big data in the lab to expert knowledge in the field. Featuring Landing AI Founder Andrew Ng

Orchestrate all the Things

00:00

Computer Vision

I presume you probably are starting with a base model and then fine cuning and customising that. A uppos to starting from scrats, right? Yes. So i think that we'll see something similar in a computer vision o many people have been pre training on emishnet for many years now. And so i think the gradual trend will be to train on a pre train on larger and larger datiss a,. increasingly on unlabele datuss, rather tan just label datuss. And increasingly a little bit more invidior rather than just on images. There's also that gradual improvement on inequality of the pre trained models.

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