Evaluating models without test data (Practical AI #194)
Changelog Master Feed
00:00
Deep Learning and Engineering Principles
Part of the tool is building open source community. And I think there are a lot of people may have ideas and we'll be able to contribute in ways that just expand it. Right now, I think deep learning is so brute force. It's like you spend as much money as you can, do as much brute force as you can. If it doesn't work, you try it again. There's no principles behind what you're doing. You build bridges by having engineering principles. And you try to build bridges that actually stay up.
Transcript
Play full episode
