Please join Jinjun Xiong, program director for cognitive computing systems research at the IBM Thomas J. Watson Research Center, for the seminar, “From statistical timing analysis to statistical convolutional neural network – A tale of two fields for AI research,” on Friday, May 31, 2019!
From statistical timing analysis to statistical convolutional neural network – A tale of two fields for AI research
Jinjun Xiong, program director for cognitive computing systems research at the IBM Thomas J. Watson Research Center
Friday, May 31, 2019
10:30 a.m.
Brickyard (BYENG) 420, Tempe campus [map]
Abstract
Arguably, research progress in deep neural networks sparked the recent surging interests in artificial intelligence (AI) from both the public media and the academia alike. Deep convolutional neural networks (CNNs) were leading the wave in achieving accuracy comparable with that of human beings in various tasks, computer vision in particular, such as image recognition, object detection and tracking. Most of these CNNs, however, operate on deterministic numbers and process one single frame of image at a time, and may not fully utilize the temporal and contextual correlation typically present in multiple channels of the same image or adjacent frames from a video.
In this talk, based on the well-established statistical timing analysis foundations in the EDA domain, we propose a novel statistical convolutional neural network (SCNN), which extends existing CNN architectures but operates directly on correlated distributions rather than deterministic numbers. Preliminary experimental results on object detection showed the great potential of this new type of SCNN, which warrants further cross-disciplinary collaboration between the two fields.
About the speaker
Jinjun Xiong is currently the program director for cognitive computing systems research at the IBM Thomas J. Watson Research Center. He is responsible for defining the scientific agenda and strategic directions for advanced cognitive computing systems research across industries, academia and governmental agencies. In that capacity, he founded and co-directs the IBM-Illinois center for cognitive computing systems research {C3SR.com). He was also a founding Pl for the IBM smarter energy research institute (SERI) with deep collaboration with a number of large electrical utility companies worldwide. The technologies he developed has been implemented inside IBM’s flagship EinsTimer/EinsStat tools, design and test methodologies used for designing multi-generations of IBM’s high performance ASICs and processors. His publication won five best paper awards and eight nominations for best paper awards. He has also led teams to win various international research competitions.
