Wednesday, November 01, 2017

Google’s Artificial-Intelligence Wizard Unveils a New Twist on Neural Networks | WIRED

Capsules with context

"Roland Memisevic, cofounder of image-recognition startup Twenty Billion Neurons, and a professor at University of Montreal, says Hinton’s basic design should be capable of extracting more understanding from a given amount of data than existing systems. If proven out at scale, that could be helpful in domains such as healthcare, where image data to train AI systems is much scarcer than the large volume of selfies available around the internet.

In some ways, capsule networks are a departure from a recent trend in AI research. One interpretation of the recent success of neural networks is that humans should encode as little knowledge as possible into AI software, and instead make them figure things out for themselves from scratch. Gary Marcus, a professor of psychology at NYU who sold an AI startup to Uber last year, says Hinton’s latest work represents a welcome breath of fresh air. Marcus argues that AI researchers should be doing more to mimic how the brain has built-in, innate machinery for learning crucial skills like vision and language. “It’s too early to tell how far this particular architecture will go, but it’s great to see Hinton breaking out of the rut that the field has seemed fixated on,” Marcus says."
Google’s Artificial-Intelligence Wizard Unveils a New Twist on Neural Networks | WIRED

No comments: