A Developmental Neuro-Robotics Approach for Boosting the Recognition of Handwritten Digits

DI NUOVO, Alessandro (2020). A Developmental Neuro-Robotics Approach for Boosting the Recognition of Handwritten Digits. In: 2020 International Joint Conference on Neural Networks (IJCNN). IEEE.

wcci2020_adinuovo.final.pdf - Accepted Version
All rights reserved.

Download (511kB) | Preview
Official URL: https://ieeexplore.ieee.org/document/9206857
Link to published version:: https://doi.org/10.1109/IJCNN48605.2020.9206857


Developmental psychology and neuroimaging research identified a close link between numbers and fingers, which can boost the initial number knowledge in children. Recent evidence shows that a simulation of the children's embodied strategies can improve the machine intelligence too. This article explores the application of embodied strategies to convolutional neural network models in the context of developmental neurorobotics, where the training information is likely to be gradually acquired while operating rather than being abundant and fully available as the classical machine learning scenarios. The experimental analyses show that the proprioceptive information from the robot fingers can improve network accuracy in the recognition of handwritten Arabic digits when training examples and epochs are few. This result is comparable to brain imaging and longitudinal studies with young children. In conclusion, these findings also support the relevance of the embodiment in the case of artificial agents’ training and show a possible way for the humanization of the learning process, where the robotic body can express the internal processes of artificial intelligence making it more understandable for humans.

Item Type: Book Section
Additional Information: © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. 2020 International Joint Conference on Neural Networks (IJCNN), 19-24 July 2020, Glasgow, UK. Series ISSN: 2161-4407
Identification Number: https://doi.org/10.1109/IJCNN48605.2020.9206857
SWORD Depositor: Symplectic Elements
Depositing User: Symplectic Elements
Date Deposited: 01 Apr 2020 16:07
Last Modified: 17 Mar 2021 22:17
URI: https://shura.shu.ac.uk/id/eprint/26014

Actions (login required)

View Item View Item


Downloads per month over past year

View more statistics