#244: Jason Devitt and Tarani Duncan of Compound Eye
Autonocast
00:00
How to Train a Neural Network to Reason About the Image
Using geometric principles, based on this concept of parallax. Minimum viable way to do that is with two cameras with an overlapping field of view. The other wholly different way that you can figure ad from an image is by using what tyronny referred to as samanticus. It means recognizing that things that are small are probably far away, and things that are big are probably close.
Transcript
Play full episode
