How computers learn to recognize objects instantly | Joseph Redmon

Ten years ago, researchers thought that getting a computer to tell the difference between a cat and a dog would be almost impossible. Today, computer vision systems do it with greater than 99 percent accuracy. How? Joseph Redmon works on the YOLO (You Only Look Once) system, an open-source method of object detection that can identify objects in images and video -- from zebras to stop signs -- with lightning-quick speed. In a remarkable live demo, Redmon shows off this important step forward for applications like self-driving cars, robotics and even cancer detection.

Om Podcasten

From the construction of virtual realities to the internet of things to the watches on our wrists—technology's influence is everywhere. Its role in our lives is evolving fast, and we're faced with riveting questions and tough challenges that sit at the intersection of technology and humanity. Listen in every Friday, with host, journalist Sherrell Dorsey, as TED speakers explore the way tech shapes how we think about society, science, design, business, and more.Follow Sherrell on Instagram @sherrell_dorsey and on LinkedIn @sherrelldorsey Hosted on Acast. See acast.com/privacy for more information.