报告题目：On Numerical Cognition Ability of Deep Learning – a case study of general AI

报告时间：2023年12月15日上午9:00

报告地点：金沙集团wwW3354CC八楼报告厅

报告人：武筱林

报告人国籍：加拿大

报告人单位：麦克马斯特大学

报告人简介：武筱林，1982金沙集团wwW3354CC学士，1988卡尔加里大学博士，专业均为计算机科学。他现在是加拿大麦克马斯特大学电子与计算机工程系教授，工学院杰出教授，加拿大国家科学与工程基金资深工业研究教授。曾经任纽约大学工学院计算机科学系研究教授（2001-2003），加拿大西部大学计算机科学系副教授、教授。武筱林教授是高精度影像处理、编码、传输及重构技术领域里的国际著名学者和技术权威。在斯坦福大学学术影响排品中，被列入世界top 1% scientists, H-index=66，拥有多项颇具影响的开创性科研成果。他是IEEE Fellow，IEEE工业信号处理委员会执行委员，IEEE多维信号处理技术委员会常务委员，IEEE图像处理汇刊副主编。他还曾任IEEE多媒体汇刊副主编；多届IEEE图像处理/信号处理大会技术委员会成员和分会主席。武筱林教授还获得过UWO卓越研究教授奖、丹麦Monsteds研究奖、芬兰诺基亚国际研究奖、VCIP最佳论文奖等国际荣誉。

报告摘要：Subitizing, or the sense of small natural numbers, is an innate cognitive function of humans and primates; it responds to visual stimuli prior to the development of any symbolic skills, language or arithmetic. 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 somewhat disappointingly, 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, a task that children perform with high accuracy and confidence.  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 mixed and interesting, pointing to both cognitive deficit of pure DL, and some measured successes of boosting DL by predetermined cognitive implements. This case study of DL in cognitive computing is meaningful as numerosity represents a rudimentary level of human intelligence.  

邀请人：杜博