The asymmetric transfers of visual perceptual learning determined by the stability of geometrical invariants

Author:

Yang Yan12ORCID,Zhuo Yan1,Zuo Zhentao132ORCID,Zhuo Tiangang132ORCID,Chen Lin132

Affiliation:

1. State Key Laboratory of Brain and Cognitive Science, Institute of Biophysics, Chinese Academy of Sciences

2. University of Chinese Academy of Sciences, Chinese Academy of Sciences

3. Hefei Comprehensive National Science Center, Institute of Artificial Intelligence

Abstract

We could recognize the dynamic world quickly and accurately benefiting from extracting invariance from highly variable scenes, and this process can be continuously optimized through visual perceptual learning. It is widely accepted that more stable invariants are prior to be perceived in the visual system. But how the structural stability of invariants affects the process of perceptual learning remains largely unknown. We designed three geometrical invariants with varying levels of stability for perceptual learning: projective (e.g., collinearity), affine (e.g., parallelism), and Euclidean (e.g., orientation) invariants, following the Klein’s Erlangen program. We found that the learning effects of low-stability invariants could transfer to those with higher stability, but not vice versa. To uncover the mechanism of the asymmetric transfers, we used deep neural networks to simulate the learning procedure and further discovered that more stable invariants were learned faster. Additionally, the analysis of the network’s weight changes across layers revealed that training on less stable invariants induced more changes in lower layers. These findings suggest that the process of perceptual learning in extracting different invariants is consistent with the Klein hierarchy of geometries and the relative stability of the invariants plays a crucial role in the mode of learning and generalization.

Publisher

eLife Sciences Publications, Ltd

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3