A Developmental Approach to Machine Learning?
A Developmental Approach to Machine Learning?
复制标题
DOI：
10.3389/fpsyg.2017.02124
复制
发表时间：
2017
影响因子：
3.8
通讯作者：
Slone LK
中科院分区：
文献类型：
--
作者：
Smith LB;Slone LK
视觉学习依赖于算法和训练材料。本文研究了婴幼儿自我中心视觉的自然统计。这些用于人类视觉对象识别的自然训练集与输入到机器视觉系统中的训练数据有很大的不同。蹒跚学步的孩子经历的不是所有事情的平等经历，而是极其不对称的分布，极少数事情多次重复发生。尽管作为一个整体非常多变，但个人对事物的看法是以特定的顺序体验的--缓慢而流畅的视觉变化，以及场景内容的发展有序的过渡。我们认为，婴幼儿倾斜、有序、有偏见的视觉体验是训练数据，它允许人类学习者开发一种方法来识别一切事物，包括无处不在的存在实体和很少遇到的实体。人类和机器学习的研究人员为了学习而联合考虑真实世界的统计数据，似乎可能会带来这两个学科的进步。
Visual learning depends on both the algorithms and the training material. This essay considers the natural statistics of infant- and toddler-egocentric vision. These natural training sets for human visual object recognition are very different from the training data fed into machine vision systems. Rather than equal experiences with all kinds of things, toddlers experience extremely skewed distributions with many repeated occurrences of a very few things. And though highly variable when considered as a whole, individual views of things are experienced in a specific order – with slow, smooth visual changes moment-to-moment, and developmentally ordered transitions in scene content. We propose that the skewed, ordered, biased visual experiences of infants and toddlers are the training data that allow human learners to develop a way to recognize everything, both the pervasively present entities and the rarely encountered ones. The joint consideration of real-world statistics for learning by researchers of human and machine learning seems likely to bring advances in both disciplines.
登录
查看更多内容
影响因子：
19.9
作者：
Byrge, Lisa;Sporns, Olaf;Smith, Linda B.
通讯作者：
Smith, Linda B.
影响因子：
64.8
作者：
Ahissar, M;Hochstein, S
通讯作者：
Hochstein, S
影响因子：
4.6
作者：
Gershkoff-Stowe, L;Smith, LB
通讯作者：
Smith, LB
影响因子：
3.4
作者：
ELMAN, JL
通讯作者：
ELMAN, JL
影响因子：
3.7
作者：
James, Karin H.;Jones, Susan S.;Smith, Linda B.
通讯作者：
Smith, Linda B.