research-article

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

Authors:

Kazuma Matsumoto,

Takato Tatsumi,

Keiki TakadamaAuthors Info & Claims

GECCO '18: Proceedings of the Genetic and Evolutionary Computation Conference Companion

Pages 1418 - 1425

https://doi.org/10.1145/3205651.3208281

Published: 06 July 2018 Publication History

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.

References

[1]

Mani Abedini and Michael Kirley. 2011. AI 2011: Advances in Artificial Intelligence: 24th Australasian Joint Conference, Perth, Australia, December 5--8, 2011. Proceedings. Springer Berlin Heidelberg, Berlin, Heidelberg, Chapter Guided Rule Discovery in XCS for High-Dimensional Classification Problems, 1--10.

Digital Library

[2]

Martin. V. Butz, David E. Goldberg, and Kurian Tharakunnel. 2003. Analysis and Improvement of Fitness Exploitation in XCS: Bounding Models, Tournament Selection, and Bilateral Accuracy. Evolutionary Computation 11, 3 (2003), 239--277.

Digital Library

[3]

Garrison W Cottrell and Paul Munro. 1988. Principal components analysis of images via back propagation. In Visual Communications and Image Processing '88: Third in a Series. International Society for Optics and Photonics, 1070--1077.

[4]

David E Golberg. 1989. Genetic algorithms in search, optimization, and machine learning. Addion wesley 1989 (1989).

Digital Library

[5]

Geoffrey E Hinton, Simon Osindero, and Yee-Whye Teh. 2006. A fast learning algorithm for deep belief nets. Neural computation 18, 7 (2006), 1527--1554.

Digital Library

[6]

Geoffrey E Hinton and Ruslan R Salakhutdinov. 2006. Reducing the dimensionality of data with neural networks. Science 313, 5786 (2006), 504--507.

[7]

Muhammad Iqbal, Will N Browne, and Mengjie Zhang. 2014. Reusing building blocks of extracted knowledge to solve complex, large-scale boolean problems. Evolutionary Computation, IEEE Transactions on 18, 4 (2014), 465--480.

[8]

H John. 1986. Holland. Escaping brittleness: The possibilities of general-purpose learning algorithms applied to parallel rule-based systems. Machine learning, an artificial intelligence approach 2 (1986), 593--623.

[9]

Yann LeCun, Léon Bottou, Yoshua Bengio, and Patrick Haffner. 1998. Gradient-based learning applied to document recognition. Proc. IEEE 86, 11 (1998), 2278--2324.

[10]

Kazuma Matsumoto, Takato Tatsumi, Hiroyuki Sato, Tim Kovacs, and Keiki Takadama. 2017. XCSR Learning from Compressed Data Acquired by Deep Neural Network (Special Issue on Cutting Edge of Reinforcement Learning and its Applications). Journal of advanced computational intelligence and intelligent informatics 21, 5 (2017), 856--867.

[11]

Warren S McCulloch and Walter Pitts. 1943. A logical calculus of the ideas immanent in nervous activity. The bulletin of mathematical biophysics 5, 4 (1943), 115--133.

[12]

David E Rumelhart, Geoffrey E Hinton, and Ronald J Williams. 1988. Learning representations by back-propagating errors. Cognitive modeling 5 (1988), 3.

[13]

Richard S Sutton. 1988. Learning to predict by the methods of temporal differences. Machine learning 3, 1 (1988), 9--44.

Digital Library

[14]

Stewart W Wilson. 1995. Classifier fitness based on accuracy. Evolutionary computation 3, 2 (1995), 149--175.

Digital Library

[15]

Stewart. W. Wilson. 1995. Classifier Fitness Based on Accuracy. Evolutionary Computation 3, 2 (June 1995), 149--175.

Digital Library

[16]

Stewart W Wilson. 2000. Get real! XCS with continuous-valued inputs. In Learning Classifier Systems. Springer, 209--219.

Digital Library

Cited By

Smierzchała ŁKozłowski NUnold O(2023)Anticipatory Classifier System With Episode-Based Experience ReplayIEEE Access10.1109/ACCESS.2023.326987911(41190-41204)Online publication date: 2023
https://doi.org/10.1109/ACCESS.2023.3269879
Sugawara RNakata M(2022)Theoretical Analysis of Accuracy-Based Fitness on Learning Classifier SystemsIEEE Access10.1109/ACCESS.2022.318361810(64862-64872)Online publication date: 2022
https://doi.org/10.1109/ACCESS.2022.3183618
Hamasaki KNakata M(2022)Minimum Rule-Repair Algorithm for Supervised Learning Classifier Systems on Real-Valued Classification TasksMetaheuristics and Nature Inspired Computing10.1007/978-3-030-94216-8_11(137-151)Online publication date: 21-Feb-2022
https://doi.org/10.1007/978-3-030-94216-8_11
Show More Cited By

Index Terms

XCSR based on compressed input by deep neural network for high dimensional data
1. Computing methodologies
  1. Machine learning
    1. Machine learning approaches
      1. Rule learning

Recommendations

PCA for improving the performance of XCSR in classification of high-dimensional problems
GECCO '11: Proceedings of the 13th annual conference companion on Genetic and evolutionary computation

XCSR is an accuracy-based learning classifier system (LCS) which can handle classification problems with real-value features. However, as the number of features increases, a high classification accuracy comes at the cost of more resources: larger ...
Adder Wavelet for Better Image Classification under Adder Neural Network
CSAI '22: Proceedings of the 2022 6th International Conference on Computer Science and Artificial Intelligence

Adder neural network (AdderNet) is a new kind of deep learning model in which the original massive multiplications in convolutions are replaced by additions. The overall energy consumption using adder network is reduced significantly. However, there is ...
XCSR with computed continuous action
AI'12: Proceedings of the 25th Australasian joint conference on Advances in Artificial Intelligence

Wilson extended XCS with interval based conditions to XCSR to handle real valued inputs. However, the possible actions must always be determined in advance. Yet domains such as robot control require numerical actions, so that neither XCS nor XCSR with ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Conferences

GECCO '18: Proceedings of the Genetic and Evolutionary Computation Conference Companion

July 2018

1968 pages

ISBN:9781450357647

DOI:10.1145/3205651

Editor:
Hernan Aguirre
Shinshu University
,
General Chair:
Keiki Takadama
The University of Electro-Communications

Copyright © 2018 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGEVO: ACM Special Interest Group on Genetic and Evolutionary Computation

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 06 July 2018

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Conference

GECCO '18

Sponsor:

SIGEVO

GECCO '18: Genetic and Evolutionary Computation Conference

July 15 - 19, 2018

Kyoto, Japan

Acceptance Rates

Overall Acceptance Rate 1,669 of 4,410 submissions, 38%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

10
Total Citations
View Citations
153
Total Downloads

Downloads (Last 12 months)3
Downloads (Last 6 weeks)0

Reflects downloads up to 14 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Smierzchała ŁKozłowski NUnold O(2023)Anticipatory Classifier System With Episode-Based Experience ReplayIEEE Access10.1109/ACCESS.2023.326987911(41190-41204)Online publication date: 2023
https://doi.org/10.1109/ACCESS.2023.3269879
Sugawara RNakata M(2022)Theoretical Analysis of Accuracy-Based Fitness on Learning Classifier SystemsIEEE Access10.1109/ACCESS.2022.318361810(64862-64872)Online publication date: 2022
https://doi.org/10.1109/ACCESS.2022.3183618
Hamasaki KNakata M(2022)Minimum Rule-Repair Algorithm for Supervised Learning Classifier Systems on Real-Valued Classification TasksMetaheuristics and Nature Inspired Computing10.1007/978-3-030-94216-8_11(137-151)Online publication date: 21-Feb-2022
https://doi.org/10.1007/978-3-030-94216-8_11
Nakamura YHoriuchi MNakata MKrawiec K(2021)Convergence analysis of rule-generality on the XCS classifier systemProceedings of the Genetic and Evolutionary Computation Conference10.1145/3449639.3459274(332-339)Online publication date: 26-Jun-2021
https://dl.acm.org/doi/10.1145/3449639.3459274
Irfan MJiangbin ZIqbal MArif M(2021)A novel lifelong learning model based on cross domain knowledge extraction and transfer to classify underwater imagesInformation Sciences10.1016/j.ins.2020.11.048552(80-101)Online publication date: Apr-2021
https://doi.org/10.1016/j.ins.2020.11.048
Irfan MJiangbin ZIqbal MArif M(2021)Enhancing learning classifier systems through convolutional autoencoder to classify underwater imagesSoft Computing10.1007/s00500-021-05738-wOnline publication date: 30-Mar-2021
https://doi.org/10.1007/s00500-021-05738-w
Horiuchi MNakata MCoello Coello C(2020)Self-adaptation of XCS learning parameters based on learning theoryProceedings of the 2020 Genetic and Evolutionary Computation Conference10.1145/3377930.3389814(342-349)Online publication date: 25-Jun-2020
https://dl.acm.org/doi/10.1145/3377930.3389814
Pätzel DStein ANakata MCoello Coello C(2020)An overview of LCS research from IWLCS 2019 to 2020Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion10.1145/3377929.3398105(1782-1788)Online publication date: 8-Jul-2020
https://dl.acm.org/doi/10.1145/3377929.3398105
Liu YBrowne WXue BAuger AStützle T(2019)Absumption to complement subsumption in learning classifier systemsProceedings of the Genetic and Evolutionary Computation Conference10.1145/3321707.3321719(410-418)Online publication date: 13-Jul-2019
https://dl.acm.org/doi/10.1145/3321707.3321719
Tadokoro MHasegawa STatsumi TSato HTakadama K(2019)Knowledge Extraction from XCSR Based on Dimensionality Reduction and Deep Generative Models2019 IEEE Congress on Evolutionary Computation (CEC)10.1109/CEC.2019.8790119(1883-1890)Online publication date: Jun-2019
https://doi.org/10.1109/CEC.2019.8790119

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents