/* ---- Google Analytics Code Below */

Tuesday, November 07, 2017

Hinton and Capsule Networks

We followed neural networks from their earliest days, but where they failed they did not have the data to consistently work under changing context, and at high enough speed, say for analyzing real-time video.  Geoffrey Hinton's work brought a new approach forward.  Now he addresses some of the lingering problems with these methods:  speed, error rates and the need for huge amounts of data. Tech papers pointed to in the link below.

Google's AI Wizard Takes a New Twist on Neural Networks in Wired, by Tom Simonite.

" ... But Hinton now belittles the technology he helped bring to the world. “I think the way we’re doing computer vision is just wrong,” he says. “It works better than anything else at present but that doesn’t mean it’s right.”

In its place, Hinton has unveiled another “old” idea that might transform how computers see—and reshape AI. That’s important because computer vision is crucial to ideas such as self-driving cars, and having software that plays doctor.

Late last week, Hinton released two research papers that he says prove out an idea he’s been mulling for almost 40 years. “It’s made a lot of intuitive sense to me for a very long time, it just hasn’t worked well,” Hinton says. “We’ve finally got something that works well.”

Hinton’s new approach, known as capsule networks, is a twist on neural networks intended to make machines better able to understand the world through images or video. In one of the papers posted last week, Hinton’s capsule networks matched the accuracy of the best previous techniques on a standard test of how well software can learn to recognize handwritten digits.

In the second, capsule networks almost halved the best previous error rate on a test that challenges software to recognize toys such as trucks and cars from different angles. Hinton has been working on his new technique with colleagues Sara Sabour and Nicholas Frosst at Google’s Toronto office.

Capsule networks aim to remedy a weakness of today’s machine-learning systems that limits their effectiveness. Image-recognition software in use today by Google and others needs a large number of example photos to learn to reliably recognize objects in all kinds of situations. That’s because the software isn’t very good at generalizing what it learns to new scenarios, for example understanding that an object is the same when seen from a new viewpoint.   ...." 

No comments: