A Database for Learning Numbers by Visual Finger Recognition in Developmental Neuro-Robotics.
A Database for Learning Numbers by Visual Finger Recognition in Developmental Neuro-Robotics.
复制标题
一个用于发展性神经机器人学中通过视觉手指识别学习数字的数据库 。
DOI：
10.3389/fnbot.2021.619504
复制
发表时间：
2021
影响因子：
3.1
通讯作者：
Di Nuovo A
中科院分区：
文献类型：
--
作者：
Davies S;Lucas A;Ricolfe-Viala C;Di Nuovo A
数字认知是人类智能的一个基本组成部分，目前尚未被完全理解。事实上，它是许多学科的研究课题，如神经科学、教育学、认知与发展心理学、数学哲学、语言学等。在人工智能领域，人们已通过神经网络对数字认知的各个方面进行建模，以复制并分析研究儿童的行为。然而，人工模型需要纳入来自身体的真实感官运动信息，才能充分模拟儿童的学习行为，例如利用手指来学习和操作数字。为此，本文介绍了一个图像数据库，该数据库聚焦于人类和机器人手部用手指表示数字的情况，可为在人形机器人中构建新的、真实的数字认知模型奠定基础，从而在发育型自主智能体中实现一种基于具身的学习方法。本文对数据库中的数据集进行了基准分析，这些数据集用于训练、验证和测试五个先进的深度神经网络，并对这些网络的分类准确率进行了比较，同时分析了每个网络的计算需求。讨论强调了在机器人实际应用所需的检测过程中速度与精度之间的权衡。
Numerical cognition is a fundamental component of human intelligence that has not been fully understood yet. Indeed, it is a subject of research in many disciplines, e.g., neuroscience, education, cognitive and developmental psychology, philosophy of mathematics, linguistics. In Artificial Intelligence, aspects of numerical cognition have been modelled through neural networks to replicate and analytically study children behaviours. However, artificial models need to incorporate realistic sensory-motor information from the body to fully mimic the children's learning behaviours, e.g., the use of fingers to learn and manipulate numbers. To this end, this article presents a database of images, focused on number representation with fingers using both human and robot hands, which can constitute the base for building new realistic models of numerical cognition in humanoid robots, enabling a grounded learning approach in developmental autonomous agents. The article provides a benchmark analysis of the datasets in the database that are used to train, validate, and test five state-of-the art deep neural networks, which are compared for classification accuracy together with an analysis of the computational requirements of each network. The discussion highlights the trade-off between speed and precision in the detection, which is required for realistic applications in robotics.
登录
查看更多内容
影响因子：
3.9
作者：
Aly, Walaa;Aly, Saleh;Almotairi, Sultan
通讯作者：
Almotairi, Sultan
影响因子：
1.7
作者：
Conti, Daniela;Di Nuovo, Santo;Di Nuovo, Alessandro
通讯作者：
Di Nuovo, Alessandro
一个充满数字的手：算术学习中卸载的角色？
影响因子：
3.8
作者：
Costa AJ;Silva JB;Chagas PP;Krinzinger H;Lonneman J;Willmes K;Wood G;Haase VG
通讯作者：
Haase VG
影响因子：
3.1
作者：
Chaudhary, Ankit;Raheja, J. L.
通讯作者：
Raheja, J. L.
影响因子：
3
作者：
Dackermann, Tanja;Fischer, Ursula;Moeller, Korbinian
通讯作者：
Moeller, Korbinian