Not only did a Cornell CIS research paper receive the best paper award at the Conference on Computer Vision and Pattern Recognition (CVPR 2017), it also got a shoutout on Facebook from the site’s founder, Mark Zuckerberg, on July 25.

Cornell researchers Gao Huang, a postdoctoral fellow in the Department of Computer Science; Zhuang Liu of Tsinghua University; Kilian Weinberger, associate professor of computer science; and Laurens van der Maaten of Facebook received congratulations from Zuckerberg for their work on “Densely Connected Convolutional Networks” on his Facebook account.

Said Zuckerberg: “One reason I’m so optimistic about AI is that improvements like this research improve systems across so many different fields – from diagnosing diseases to keep us healthy, to improving self-driving cars to keep us safe, and from showing you better content in [Facebook’s] News Feed to delivering you more relevant search results. Every time we improve our AI methods, all of these systems get better. I’m excited about all the progress here and it’s potential to make the world better.”

The team found that neural networks whose layers are all connected to each other perform better than the current state-of-the-art residual neural networks. In their paper, the authors introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion.

“This radically changes the information flow in the network,” said lead researcher Weinberger. “Because every neuron has access to all prior computations, it turns out DenseNets can be far more parameter-efficient – an essential feature on modern hardware, where networks are typically limited by the size of the CPU memory.”

What makes this research relevant to Facebook and its AI team is its accuracy and smaller memory size. “Facebook users upload around 250 million images per day,” said Weinberger. “To utilize the data they have, which is their main asset, Facebook needs some way to do this more efficiently and with higher accuracy. This could translate into cost savings through reduced computational demand and may also unlock new possibilities because these networks make fewer errors.”

Leslie Morris is director of communications for Computing and Information Science.