Yannic Kilcher Videos (Audio Only) cover image

Self-driving from VISION ONLY - Tesla's self-driving progress by Andrej Karpathy (Talk Analysis)

Yannic Kilcher Videos (Audio Only)

00:00

The Architecture of the Neural Network

We have these images coming from multiple cameras on the top. All of them are processed by an image extractor, like a backbone,. Then there's a multi-confusion that uses the information from all the ATUs. And then we fuse information first across all the cameras and then across all of time. The data set they come up with is 1.5 petabytes crazy. We've done seven rounds of shadow mode for this release. So you're driving yourself, but the system predicts all the time.

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