The Openness of Machine Learning Frameworks

Back then the frameworks they were there, they were lower level, they were doing less work. And so the people who use them therefore had to do more, but then also had more leeway to make them better in certain ways. Whereas today, of course, with the relative standardization, everybody is using PyTorch Jack's sensor flow. Then there is a much more level playing field in that regard. Yeah. That's really interesting. And that makes a lot of sense to me.

Transcript

Play full episode

Transcript

Episode notes

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!

Get the app