
Machines Learn Better if We Teach Them the Basics
The Quanta Podcast
00:00
The Rise of Computer Vision
Machines have struggled to understand human language and decipher images in the first place. Two natural language processing models allow machines to essentially learn the meaning behind words and sentences. Computer vision has seen a similar digital explosion. Around 2009, ImageNet debuted as a database of annotated images for computer vision research. Today it hosts over 14 million images of objects and places. programs like OpenAI's Dolly generate new images upon command that look human-made despite having no exact comparison to draw from.
Transcript
Play full episode