Since deep learning became popular ten years ago, computer vision is adopted by a wide range of applications. Many applications must run on embedded systems with limited resources. This speech will introduce a new architecture called modular neural network that can significantly reduce the sizes of machine models and execution time. A modular neural network is a tree-like structure to progressively analyze different features in images and divide images into different groups based on visual similarities. Modular neural networks can be used for image classification, object counting, and re-identification. This speech will also explain how to use contextual information to reduce computation for convolution.

Yung-Hsiang Lu is a professor of Electrical and Computer Engineering at Purdue University. He is a fellow of the IEEE and distinguished scientist of the ACM. Dr. Lu is the inaugural director of Purdue’s John Martinson Engineering Entrepreneurial Center. He has advised multiple student teams winning business plan competitions; two teams of students started technology companies and raised more than $1.5M. Dr. Lu is the lead organizer of the IEEE Low-Power Computer Vision Challenge since 2015. "Low-Power Computer Vision: Improve the Efficiency of Artificial Intelligence" (ISBN 9780367744700) is a new book of articles written by the winners.