AI Can Now Recognize Objects After Seeing Just One Example

In Brief A new AI algorithm developed by DeepMind researchers requires samples from just a few hundred image categories before it can recognize an object after just one example. Any field that uses artificial intelligence could benefit from “one-shot learning” systems that learn more accurately and more quickly than current AI. Faster Learning Advances in machine learning and deep learning systems are bring us much closer to developing true artificial intelligence (AI) than ever before. One major limitation to these systems, though, is the effort required to teach them, with most requiring thousands or even hundreds of thousands of examples before they can “learn” something new. Self-driving car systems absorb miles of traffic data to learn basic driving lessons, and this scary image generator had to be fed 200,000 images for it…


Link to Full Article: AI Can Now Recognize Objects After Seeing Just One Example

Pin It on Pinterest

Share This