arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.05160cs.CV
收藏

深度学习在数量上的认知缺陷

Cognitive Deficit of Deep Learning in Numerosity

McMaster University(麦克马斯特大学);Shanghai Jiao Tong University(上海交通大学)

Xiaolin Wu, Xi Zhang, Xiao Shu

摘要:

Subitizing,或小自然数的感觉,是人类和灵长类动物与生俱来的认知功能;它在任何符号技能,语言或算术发展之前对视觉刺激做出反应。鉴于深度学习(DL)在视觉智能任务中的成功,以及数字感的非线性,一个诱人的问题是DL是否可以理解数字并执行subitizing。但令人有些困惑的是,认知心理学类型的大量实验表明,由示例驱动的黑盒深度学习无法看穿视觉表征中的表面变化,也无法提取自然数的抽象概念,而儿童在完成这项任务时具有很高的准确性和信心。失败显然是由于学习方法,而不是CNN计算机器本身。确实存在能够subitizing的递归神经网络,我们通过将数学形态学机制编码到CNN卷积核中来构建它。此外,我们调查,使用subitizing作为一个测试床,如何帮助黑盒DL的认知先验来自人类的洞察力。我们的研究结果是混合的和有趣的,既指向纯DL的认知缺陷,和一些测量成功的提高DL预定的认知工具。这个认知计算中深度学习的案例研究是有意义的,因为视觉数字代表了人类智能的最低水平。

英文摘要:

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 CNN computational 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 for visual numerosity represents a minimum level of human intelligence.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑