Skip to main content

Research Repository

Advanced Search

Unsupervised temporospatial neural architecture for sensorimotor map learning.

Ezenkwu, Chinedu Pascal; Starkey, Andrew

Authors

Andrew Starkey



Abstract

The ability to learn the sensorimotor maps of unknown environments without supervision is a vital capability of any autonomous agent, be it biological or artificial. An accurate sensorimotor map should be able to encode the agent's world and equip it with the capability to anticipate or predict the results of its actions. However, to design a robust autonomous learning technique for an unknown, dynamic, partially observable, or noisy environment remains a daunting task. This article proposes a temporospatial merge grow when required (TMGWR) network for continuous self-organization of an agent's sensorimotor awareness in noisy environments. TMGWR is an adaptive neural algorithm that learns the sensorimotor map of an agent's world using a time series self-organizing strategy and the grow when required (GWR) algorithm. The algorithm is compared with growing neural gas (GNG), GWR, and time GNG in terms of their disambiguation performance, sensorial representation accuracy, and sensorimotor-link error, a new metric that is developed in this article to evaluate how well a sensorimotor map represents causality in the agent's world. The outcomes of the experiments show that TMGWR is more efficient and suitable for sensorimotor map learning in noisy environments than the competing algorithms.

Citation

EZENKWU, C.P. and STARKEY, A. 2021. Unsupervised temporospatial neural architecture for sensorimotor map learning. IEEE transactions on cognitive and developmental systems [online], 13(1), pages 223-230. Available from: https://doi.org/10.1109/TCDS.2019.2934643

Journal Article Type Article
Acceptance Date Aug 4, 2019
Online Publication Date Aug 12, 2019
Publication Date Mar 31, 2021
Deposit Date Mar 29, 2024
Publicly Available Date Apr 2, 2024
Journal IEEE transactions on cognitive and developmental systems
Print ISSN 2379-8920
Electronic ISSN 2379-8939
Publisher Institute of Electrical and Electronics Engineers (IEEE)
Peer Reviewed Peer Reviewed
Volume 13
Issue 1
Pages 223-230
DOI https://doi.org/10.1109/TCDS.2019.2934643
Keywords Autonomous agent; Causality; Dynamic environment; Sensorimotor awareness; Unsupervised learning
Public URL https://rgu-repository.worktribe.com/output/2287971

Files

EZENKWU 2021 Unsupervised temporospatial neural (AAM) (543 Kb)
PDF

Copyright Statement
© 2021 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.




You might also like



Downloadable Citations