DI NUOVO, Alessandro (2018). Long-short term memory networks for modelling embodied mathematical cognition in robots. In: World Congress on Computational Intelligence 2018, Rio de Janeiro, 8-13 July. IEEE.
|
PDF
PID5318551.pdf - Accepted Version All rights reserved. Download (752kB) | Preview |
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.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Additional Information: | Electronic ISSN: 2161-4407 |
Research Institute, Centre or Group - Does NOT include content added after October 2018: | Cultural Communication and Computing Research Institute > Communication and Computing Research Centre Materials and Engineering Research Institute > Modelling Research Centre > Microsystems and Machine Vision Laboratory |
Departments - Does NOT include content added after October 2018: | Faculty of Science, Technology and Arts > Department of Computing |
Depositing User: | Alessandro Di Nuovo |
Date Deposited: | 05 Jun 2018 08:58 |
Last Modified: | 18 Mar 2021 07:16 |
URI: | https://shura.shu.ac.uk/id/eprint/20884 |
Actions (login required)
View Item |
Downloads
Downloads per month over past year