• Main Menu
Main Menu
Menu

MSU research gets traction at NeurlPS ’19

Dec. 27, 2019

MSU team focused on artificial intelligence earns world recognition at Google MicroNet Challenge

A research team from the MSU Department of Electrical and Computer Engineering (ECE) was recognized as fourth in the world and first in the U.S. and Canada at the recent Google MicroNet Challenge in Vancouver, Canada.

ECE PhD students Yu Zheng, Shen Yan, Xiao Zeng, and Biyi Fang, and ECE Assistant Professor Mi Zhang, earn world recognition for artificial intelligence research at Google MicroNet Challenge.
ECE PhD students Yu Zheng, Shen Yan, Xiao Zeng, and Biyi Fang, and ECE Assistant Professor Mi Zhang, received world recognition for artificial intelligence research at Google MicroNet Challenge.

ECE Assistant Professor Mi Zhang and ECE PhD students Yu Zheng, Shen Yan, Xiao Zeng, and Biyi Fang were acknowledged for their contributions to the Google MicroNet Challenge CIFAR-100 Track at the conference on Neural Information Processing (NeurlPS’19), Dec. 8-14. 

(See the LeaderBoard at: https://tinyurl.com/tzpwb5u)

Zhang said the Google MicroNet Challenge looks for solutions in developing the most efficient deep neural network architecture for resource-constrained devices, such as mobile phones and Internet of Things. 

“The solution provided by the MSU team is built on an efficient backbone design with a combination of sparsification and quantization techniques. The MSU team’s solution is now open source. We hope it can push the research area of AI for mobile and IoT forward,” Zhang added.

Around 13,000 participants attended NeurIPS'19, which brings experts from around the world together to engage on the science of artificial intelligence and machine learning. The annual meeting fosters an exchange of research on neural information processing systems from biological, technological, mathematical, and theoretical perspectives.

This is the Zhang team’s third international competition win in the past four years. In 2016, the team won the Champion of the NIH Pill Image Recognition Challenge. In 2017, it took third place at the NSF Hearables Challenge.