Unsupervised Temporospatial Neural Architecture for Sensorimotor Map Learning

Chinedu Pascal Ezenkwu, Andrew Starkey

Research output: Contribution to journalArticle

2 Downloads (Pure)

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 agents 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 paper proposes a Temporospatial Merge Grow When Required (TMGWR) network for continuous self-organisation of an agents 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-organising strategy and the Grow When Required (GWR) algorithm. The algorithm is compared with GNG, GWR and TGNG in terms of their disambiguation performance, sensorial representation accuracy and sensorimotor-link error, a new metric that is developed in this paper to evaluate how well a sensorimotor map represents causality in the agents 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.

Original languageEnglish
JournalIEEE Transactions on Cognitive and Developmental Systems
Early online date12 Aug 2019
DOIs
Publication statusE-pub ahead of print - 12 Aug 2019

Fingerprint

Autonomous agents
Time series
Experiments

Keywords

  • autonomous agent
  • causality.
  • dynamic environment
  • sensorimotor awareness
  • unsupervised learning

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Cite this

@article{113614c6d86a44919719bb951858832a,
title = "Unsupervised Temporospatial Neural Architecture for Sensorimotor Map Learning",
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 agents 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 paper proposes a Temporospatial Merge Grow When Required (TMGWR) network for continuous self-organisation of an agents 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-organising strategy and the Grow When Required (GWR) algorithm. The algorithm is compared with GNG, GWR and TGNG in terms of their disambiguation performance, sensorial representation accuracy and sensorimotor-link error, a new metric that is developed in this paper to evaluate how well a sensorimotor map represents causality in the agents 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.",
keywords = "autonomous agent, causality., dynamic environment, sensorimotor awareness, unsupervised learning",
author = "Ezenkwu, {Chinedu Pascal} and Andrew Starkey",
year = "2019",
month = "8",
day = "12",
doi = "10.1109/TCDS.2019.2934643",
language = "English",
journal = "IEEE Transactions on Cognitive and Developmental Systems",
issn = "2379-8920",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Unsupervised Temporospatial Neural Architecture for Sensorimotor Map Learning

AU - Ezenkwu, Chinedu Pascal

AU - Starkey, Andrew

PY - 2019/8/12

Y1 - 2019/8/12

N2 - 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 agents 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 paper proposes a Temporospatial Merge Grow When Required (TMGWR) network for continuous self-organisation of an agents 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-organising strategy and the Grow When Required (GWR) algorithm. The algorithm is compared with GNG, GWR and TGNG in terms of their disambiguation performance, sensorial representation accuracy and sensorimotor-link error, a new metric that is developed in this paper to evaluate how well a sensorimotor map represents causality in the agents 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.

AB - 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 agents 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 paper proposes a Temporospatial Merge Grow When Required (TMGWR) network for continuous self-organisation of an agents 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-organising strategy and the Grow When Required (GWR) algorithm. The algorithm is compared with GNG, GWR and TGNG in terms of their disambiguation performance, sensorial representation accuracy and sensorimotor-link error, a new metric that is developed in this paper to evaluate how well a sensorimotor map represents causality in the agents 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.

KW - autonomous agent

KW - causality.

KW - dynamic environment

KW - sensorimotor awareness

KW - unsupervised learning

UR - http://www.scopus.com/inward/record.url?scp=85070705495&partnerID=8YFLogxK

U2 - 10.1109/TCDS.2019.2934643

DO - 10.1109/TCDS.2019.2934643

M3 - Article

AN - SCOPUS:85070705495

JO - IEEE Transactions on Cognitive and Developmental Systems

JF - IEEE Transactions on Cognitive and Developmental Systems

SN - 2379-8920

ER -