'Godfather' of deep learning is reimagining AI

November 3, 2017 by Chris Sorensen
Geoffrey Hinton, a University Professor Emeritus at U of T and a research fellow at Google, recently published two papers that may help correct one of deep learning's key shortcomings. Credit: Johnny Guatto

Geoffrey Hinton may be the "godfather" of deep learning, a suddenly hot field of artificial intelligence, or AI – but that doesn't mean he's resting on his algorithms.

Hinton, a University Professor Emeritus at the University of Toronto, recently released two new papers that promise to improve the way machines understand the world through images or video – a technology with applications ranging from self-driving cars to making medical diagnoses.

"This is a much more robust way to detect objects than what we have at present," Hinton, who is also a fellow at Google's AI research arm, said today at a tech conference in Toronto.

"If you've been in the field for a long time like I have, you know that the neural nets that we use now – there's nothing special about them. We just sort of made them up."

Hinton's latest approach, detailed in a recent story in Wired magazine, relies on something he calls "capsule networks." Here's how it works: At present, algorithms must be trained on millions of images before they can reliably distinguish a picture of, say, a cat from something else. In part, that's because the software isn't very good at applying what it's already learned to brand new situations – for example, recognizing a cat that's being viewed from a slightly different angle. Capsule networks, by contrast, can help track the relationship between various parts of an object – in the case of a cat, one example might be the relative distance between its nose and mouth.

Hinton talked about his research, co-authored with Sara Sabour and Nicholas Frosst, at Google's Go North conference, held at Toronto's Evergreen Brick Works.

With his new research, there's little doubt Hinton is doing his part to move the AI ball forward – even if it draws on ideas he's been contemplating for the past 40 years.

In one of his recently published papers, Hinton's capsule networks matched the accuracy of the best previous techniques when it comes to recognizing hand-written digits, according to Wired. The second paper cut in half the previous error rate on a test that challenges software to recognize objects like toys from different angles, the magazine said.

"What we showed is early days," Hinton cautioned attendees at Go North.

"It works quite impressively on small datasets. But until it works on large datasets, you shouldn't believe it."

Even so, other researchers are lauding Hinton's efforts.

"It's too early to tell how far this particular architecture will go," Gary Marcus, a professor of psychology at New York University, told Wired. "But it's great to see Hinton out of the rut that the field has seemed fixated on."

Explore further: Google buys machine learning startup

More information: Dynamic Routing Between Capsules, arXiv:1710.09829 [cs.CV] arxiv.org/abs/1710.09829

Matrix capsules with EM routing, openreview.net/forum?id=HJWLfGWRb¬eId=HJWLfGWRb

Related Stories

Google buys machine learning startup

March 13, 2013

Google said Wednesday that it has bought a Canadian startup specializing in getting machines to understand what people are trying to say.

Teaching machines to recognize shapes

December 12, 2011

As any parent knows, teaching a toddler to recognize objects involves trial-and-error. A child, for example, may not initially recognize a cow in a picture-book after seeing the live animal on a farm and being told its label. ...

Weight-bearing exercises promote bone formation in men

March 22, 2017

Osteoporosis affects more than 200 million people worldwide and is a serious public health concern, according to the National Osteoporosis Foundation. Now, Pamela Hinton, associate professor in the Department of Nutrition ...

Obesity and type 2 diabetes harm bone health

November 17, 2015

Obesity and Type 2 diabetes have been linked to several health issues, including an increased risk of bone fractures. In a new animal study, University of Missouri researchers examined how the development of obesity and insulin ...

Recommended for you

Team breaks world record for fast, accurate AI training

November 7, 2018

Researchers at Hong Kong Baptist University (HKBU) have partnered with a team from Tencent Machine Learning to create a new technique for training artificial intelligence (AI) machines faster than ever before while maintaining ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.