Visual number sense in untrained deep neural networks-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

Visual number sense in untrained deep neural networks

Published:2021-01 Issue:1 Volume:7 Page:
ISSN:2375-2548
Container-title:Science Advances
language:en
Short-container-title:Sci. Adv.

Author:

Kim Gwangsu¹^ORCID,Jang Jaeson²^ORCID,Baek Seungdae²^ORCID,Song Min²³^ORCID,Paik Se-Bum²³^ORCID

Affiliation:

1. Department of Physics, Korea Advanced Institute of Science and Technology, Daejeon 34141, Republic of Korea.

2. Department of Bio and Brain Engineering, Korea Advanced Institute of Science and Technology, Daejeon 34141, Republic of Korea.

3. Program of Brain and Cognitive Engineering, Korea Advanced Institute of Science and Technology, Daejeon 34141, Republic of Korea.

Abstract

Visual number sense can arise spontaneously in untrained deep neural networks in the complete absence of learning.

Funder

National Research Foundation of Korea

Publisher

American Association for the Advancement of Science (AAAS)

Subject

Multidisciplinary

Reference57 articles.

1. Psychophysical evidence for the number sense

2. Individual differences in non-verbal number acuity correlate with maths achievement

3. The neuronal code for number

4. Newborn infants perceive abstract numbers

5. Number-space mapping in the newborn chick resembles humans’ mental number line

Cited by 52 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Trained deep neural network models of the ventral visual pathway encode numerosity with robustness to object and scene identity;2024-09-10

2. Exploring Early Number Abilities With Multimodal Transformers;Cognitive Science;2024-09

3. Numerosity adaptation suppresses early visual responses;2024-08-30

4. Unsupervised Video Face Super-Resolution via Untrained Neural Network Priors;2024 International Joint Conference on Neural Networks (IJCNN);2024-06-30

5. Atomic Quantum Technologies for Quantum Matter and Fundamental Physics Applications;Technologies;2024-05-07

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