Clustering sensory inputs using NeuroEvolution of augmenting topologies

David Kadish

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

Abstract

Sorting data into groups and clusters is one of the fundamental tasks of artificially intelligent systems. Classical clustering algorithms rely on heuristic (k-nearest neighbours) or statistical methods (k-means, fuzzy c-means) to derive clusters and these have performed well. Neural networks have also been used in clustering data, but researchers have only recently begun to adopt the strategy of having neural networks directly determine the cluster membership of an input datum. This paper presents a novel strategy, employing NeuroEvolution of Augmenting Topologies to produce an evoltionary neural network capable of directly clustering unlabelled inputs. It establishes the use of cluster validity metrics in a fitness function to train the neural network.
Original languageEnglish
Title of host publicationGECCO '18: Proceedings of the Genetic and Evolutionary Computation Conference Companion
Number of pages162
PublisherAssociation for Computing Machinery
Publication dateJul 2018
Pages161
DOIs
Publication statusPublished - Jul 2018
EventGECCO '18: The Genetic and Evolutionary Computation Conference - Kyoto, Japan, Kyoto, Japan
Duration: 15 Jul 201819 Jul 2018
http://gecco-2018.sigevo.org/index.html/tiki-index.html

Conference

ConferenceGECCO '18
LocationKyoto, Japan
Country/TerritoryJapan
CityKyoto
Period15/07/201819/07/2018
Internet address

Keywords

  • Cluster Analysis
  • Neural Networks
  • NeuroEvolution of Augmenting Topologies
  • Unsupervised Learning
  • Cluster Validity Metrics

Fingerprint

Dive into the research topics of 'Clustering sensory inputs using NeuroEvolution of augmenting topologies'. Together they form a unique fingerprint.

Cite this