题  目：Can deep learning learn to count on cognitive deficit of the current state of deep learning?

报告人：武筱林 加拿大麦克马斯特大学电子与计算机工程系教授，上海交通大学特聘教授

时  间：2018-11-26 周一 下午15:00

地  点：振声苑E208

报告摘要：

Given successes of deep learning (DL) in tasks of visual intelligence and given the primitivity of number sense, a tantalizing question is whether DL can comprehend numbers and perform subitizing. But extensive experiments of the type of cognitive psychology demonstrate that the examples-driven black box DL cannot see through superficial variations in visual representations and distill the abstract notion of natural number.The failure is apparently due to the learning method not the connectionist CNN machinery itself. A recurrent neural network capable of subitizing does exist, which we construct by encoding a mechanism of mathematical morphology into the CNN convolutional kernels. Also, we investigate, using subitizing as a test bed, the ways to aid the black box DL by cognitive priors derived from human insight. Our findings are pointing to both cognitive deficit of pure DL, and some measured successes of boosting DL by predetermined cognitive implements.

报告人简介：

Xiaolin Wu, Ph.D. in computer science, University of Calgary, Canada, 1988. Dr. Wu started his academic career in 1988, and has since been on the faculty of Western University, New York Polytechnic University (NYU Poly), and currently McMaster University.He holds the NSERC senior industrial research chair in Digital Cinema. Dr. Wu is an IEEE fellow, McMaster Distinguished Engineering Professor, an associated editor of IEEE Transactions on Image Processing, and served on the technical committees of many IEEE international conferences/workshops.