Mathematical competence can endow robots with the necessary capability for abstract and symbolic processing, which is required for higher cognitive functions such as natural language understanding. But, so far, only few attempts have been made to model mathematical cognition in robots. This paper presents an experimental evaluation of the Long- Short Term Memory networks for modeling the simple mathematical operation of single-digits addition in a cognitive robot. To this end, the robotic model creates an association between the proprioceptive information from finger counting and the handwritten digits of the MNIST dataset. In practice, the model executes two tasks concurrently: It recognizes the handwritten digits in a sequence and sums them. The results show that the association with fingers can improve the robot precision, as observed in children. Also, the robot makes a disproportionate number of split-five errors similarly to what observed in studies with children and adults, hence giving evidence to support the hypothesis that these errors are due the use of a five-fingers counting system.

Long-Short Term Memory Networks for Modelling Embodied Mathematical Cognition in Robots

Di Nuovo A.
Primo
2018-01-01

Abstract

Mathematical competence can endow robots with the necessary capability for abstract and symbolic processing, which is required for higher cognitive functions such as natural language understanding. But, so far, only few attempts have been made to model mathematical cognition in robots. This paper presents an experimental evaluation of the Long- Short Term Memory networks for modeling the simple mathematical operation of single-digits addition in a cognitive robot. To this end, the robotic model creates an association between the proprioceptive information from finger counting and the handwritten digits of the MNIST dataset. In practice, the model executes two tasks concurrently: It recognizes the handwritten digits in a sequence and sums them. The results show that the association with fingers can improve the robot precision, as observed in children. Also, the robot makes a disproportionate number of split-five errors similarly to what observed in studies with children and adults, hence giving evidence to support the hypothesis that these errors are due the use of a five-fingers counting system.
2018
978-1-5090-6015-3
Cognitive Developmental Robotics; Deep Learning; Long Short-Term Memory networks; Mathematical Cognition Indexed keywords Engineering controlled terms Brain; Character recognition; Deep learning; Functions; Long short-term memory; Robotics Engineering uncontrolled terms Cognitive functions; Developmental robotics; Experimental evaluation; Mathematical Cognition; Mathematical operations; Natural language understanding; Short term memory; Symbolic processing Engineering main heading Robots Funding details Details about financial support for research, including funding sources and grant numbers as provided in academic publications. Funding sponsor Funding number Acronym Engineering and Physical Sciences Research Council See opportunities by EPSRC See opportunities (opens in new window) EP/P030033/1 EPSRC Funding text The author acknowledges the support of the EPSRC through the project grant no. EP/P030033/1 (NUMBERS). Corresponding authors Corresponding author A. Di Nuovo Affiliation Department of Computing and Sheffield Robotics, Sheffield Hallam University, Sheffield, United Kingdom Email address [email protected] © Copyright 2018 Elsevier B.V., All rights reserved. Abstract Author keywords Indexed keywords Funding details Corresponding authors
File in questo prodotto:
File Dimensione Formato  
DiNuovo_Long-Short-Term-Memory-Networks.pdf

solo utenti autorizzati

Tipologia: Versione Editoriale (PDF)
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 1.84 MB
Formato Adobe PDF
1.84 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11769/737251
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 9
  • ???jsp.display-item.citation.isi??? 1
social impact