Skip to content

XCSR based on compressed input by deep neural network for high dimensional data

Research output: Chapter in Book/Report/Conference proceedingConference contribution

  • Kazuma Matsumoto
  • Hiroyuki Sato
  • Ryo Takano
  • Tim M D Kovacs
  • Takato Tatsumi
  • Keiki Takadama
Original languageEnglish
Title of host publicationGECCO'18: 2018 Genetic and Evolutionary Computation Conference Companion
Publisher or commissioning bodyAssociation for Computing Machinery (ACM)
Pages1418-1425
Number of pages8
ISBN (Electronic)9781450357647
DOIs
DateAccepted/In press - 10 Apr 2018
DatePublished (current) - 6 Jul 2018
Event2018 Genetic and Evolutionary Computation Conference, GECCO 2018 - Kyoto, Japan
Duration: 15 Jul 201819 Jul 2018

Conference

Conference2018 Genetic and Evolutionary Computation Conference, GECCO 2018
CountryJapan
CityKyoto
Period15/07/1819/07/18

Abstract

This paper proposes the novel Learning Classifier System (LCS) which can solve high-dimensional problems, and obtain human-readable knowledge by integrating deep neural networks as a compressor. In the proposed system named DCAXCSR, deep neural network called Deep Classification Autoencoder (DCA) compresses (encodes) input to lower dimension information which LCS can deal with, and decompresses (decodes) output of LCS to the original dimension information. DCA is hybrid network of classification network and autoencoder towards increasing compression rate. If the learning is insufficient due to lost information by compression, by using decoded information as an initial value for narrowing down state space, LCS can solve high dimensional problems directly. As LCS of the proposed system, we employs XCSR which is LCS for real value in this paper since DCA compresses input to real values. In order to investigate the effectiveness of the proposed system, this paper conducts experiments on the benchmark classification problem of MNIST database and Multiplexer problems. The result of the experiments shows that the proposed system can solve high-dimensional problems which conventional XCSR cannot solve, and can obtain human-readable knowledge.

    Research areas

  • Deep Learning, LCS, Neural Network, XCS, XCSR

Event

2018 Genetic and Evolutionary Computation Conference, GECCO 2018

Duration15 Jul 201819 Jul 2018
CityKyoto
CountryJapan
Sponsorset al. (External organisation), Nature Research (External organisation), Sentient (External organisation), SparkCognition (External organisation), Springer (External organisation), Uber AI Labs (External organisation)

Event: Conference

Documents

DOI

View research connections

Related faculties, schools or groups