A Deep Neural Network for Finger Counting and Numerosity Estimation

PECYNA, Leszek, CANGELOSI, Angelo and DI NUOVO, Alessandro (2020). A Deep Neural Network for Finger Counting and Numerosity Estimation. 2019 IEEE Symposium Series on Computational Intelligence (SSCI).

Preview

PDF paper_80.pdf - Accepted Version All rights reserved. Download (768kB) | Preview

Abstract

In this paper, we present neuro-robotics models with a deep artificial neural network capable of generating finger counting positions and number estimation. We first train the model in an unsupervised manner where each layer is treated as a Restricted Boltzmann Machine or an autoencoder. Such a model is further trained in a supervised way. This type of pretraining is tested on our baseline model and two methods of pre-training are compared. The network is extended to produce finger counting positions. The performance in number estimation of such an extended model is evaluated. We test the hypothesis if the subitizing process can be obtained by one single model used also for estimation of higher numerosities. The results confirm the importance of unsupervised training in our enumeration task and show some similarities to human behaviour in the case of subitizing.

Item Type:	Article
Additional Information:	© 2019 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. Conference - Xiamen, China, 6-9 December 2019 Electronic ISBN - 9781728124858
Identification Number:	https://doi.org/10.1109/SSCI44817.2019.9002694
SWORD Depositor:	Symplectic Elements
Depositing User:	Symplectic Elements
Date Deposited:	06 Jan 2020 16:54
Last Modified:	18 Mar 2021 02:16
URI:	https://shura.shu.ac.uk/id/eprint/25605

Actions (login required)

View Item

Downloads

Publication Metrics