Abstract
The rule-based XCS Classifier System (XCS) aims at forming classifiers which are as general as possible to achieve an optimal performance level. A too high generalization pressure may lead to over-general classifiers degrading the performance of XCS. To date, no method exists for XCS for real-valued input spaces (XCSR) to handle over-general classifiers ensuring an accurate population. The Absumption mechanism and the Specify operator, both developed for XCS with binary inputs, provide a promising basis for over-generality handling in XCSR. This paper introduces adapted versions of Absumption and Specify by proposing different identification and specialization strategies for the application in XCSR. To determine their potential, the adapted techniques will be evaluated in different classification problems, i.e., common benchmarks and real-world data from the agricultural domain, and in a multi-step problem.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
6-RMP: NÂ =Â 800, \(\alpha \)Â =Â 0.1, \(\beta \)Â =Â 0.2, \(\delta \)Â =Â 0.1, \(\nu \)Â =Â 5, \(\theta _{mna}\)Â =Â 2, \(\theta _{GA}\)Â =Â 12, \(\theta _{del}\)Â =Â 20, \(\theta _{sub}\)Â =Â 20, \(\epsilon _0\)Â =Â 10, \(\chi \)Â =Â 0.8, \(\mu \)Â =Â 0.04, \(p_{ini}\)Â =Â 10.0, \(\epsilon _{ini}\)Â =Â 0.0, \(F_{ini}\)Â =Â 0.01, \(\epsilon _{red}\)Â =Â 0.25, \(F_{red}\)Â =Â 0.1, \(m_0\)Â =Â 0.1, \(r_0\)Â =Â 1.0.
- 2.
CBP(3,3): Analogous to 6-RMP, except: NÂ =Â 2000, \(r_0\)Â =Â 0.5.
- 3.
Mario: Analogous to 6-RMP, except: NÂ =Â 7000, \(\beta \)Â =Â 0.3, \(\theta _{mna}\)Â =Â 6, \(\theta _{GA}\)Â =Â 30, \(\theta _{del}\)Â =Â 50, \(\theta _{sub}\)Â =Â 50, \(r_0\)Â =Â 0.1.
- 4.
- 5.
https://data.world/uci/horse-colic (05.11.2020).
- 6.
https://data.world/uci/soybean-large (05.11.2020).
- 7.
Analogous to 6-RMP, except: NÂ =Â 6400, \(\theta _{GA}\)Â =Â 48, \(\theta _{del}\)Â =Â 50, \(\theta _{sub}\)Â =Â 50, \(\epsilon _0\)Â =Â 1.0, \(\epsilon _{red}\)Â =Â 1.0, \(m_0\)Â =Â 0.5, \(r_0\)Â =Â 1.0.
- 8.
Analogous to 6-RMP, except: NÂ =Â 10,000, \(\gamma \)Â =Â 0.95, \(\theta _{mna}\)Â =Â 4, \(\theta _{GA}\)Â =Â 50, \(\theta _{del}\)Â =Â 50, \(\theta _{sub}\)Â =Â 50, \(\epsilon _0\)Â =Â 0.005, \(m_0\)Â =Â 0.25, \(r_0\)Â =Â 0.5.
References
Bacardit, J., Burke, E.K., Krasnogor, N.: Improving the scalability of rule-based evolutionary learning. Memet. Comput. 1(1), 55–67 (2009)
Barry, A.M.: The stability of long action chains in XCS. Soft Comput. 6(3), 183–199 (2002)
Bernadó-Mansilla, E., Garrell-Guiu, J.M.: Accuracy-based learning classifier systems: models, analysis and applications to classification tasks. Evol. Comput. 11(3), 209–238 (2003)
Butz, M.V., Kovacs, T., Lanzi, P.L., Wilson, S.W.: How XCS evolves accurate classifiers. In: Proceedings of GECCO 2001. GECCO 2001, pp. 927–934. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA (2001)
Butz, M.V., Lanzi, P.L., Wilson, S.W.: Function approximation with XCS: hyperellipsoidal conditions, recursive least squares, and compaction. IEEE T Evolut. Comput. 12(3), 355–376 (2008)
Butz, M.V., Stolzmann, W.: An algorithmic description of ACS2. In: Lanzi, P.L., Stolzmann, W., Wilson, S.W. (eds.) IWLCS 2001. LNCS (LNAI), vol. 2321, pp. 211–229. Springer, Heidelberg (2002). https://doi.org/10.1007/3-540-48104-4_13
Butz, M.V., Wilson, S.W.: An algorithmic description of XCS. In: Luca Lanzi, P., Stolzmann, W., Wilson, S.W. (eds.) IWLCS 2000. LNCS (LNAI), vol. 1996, pp. 253–272. Springer, Heidelberg (2001). https://doi.org/10.1007/3-540-44640-0_15
Calian, D.A., Bacardit, J.: Integrating memetic search into the BioHEL evolutionary learning system for large-scale datasets. Memet. Comput. 5(2), 95–130 (2013)
Dorigo, M.: Genetic and non-genetic operators in ALECSYS. Evol. Comput. 1(2), 151–164 (1993)
Holland, J.H., Reitman, J.S.: Cognitive systems based on adaptive algorithms. In: Pattern-Directed Inference Systems, pp. 313–329. Academic Press (1978)
Kovacs, T.: Towards a theory of strong overgeneral classifiers. In: FOGA 6, pp. 165–184. Morgan Kaufmann, San Francisco (2001)
Lanzi, P.L.: A study on the generalization capabilities of XCS. In: Proceedings of ICGA 1997, pp. 418–425 (1997)
Lanzi, P.L.: An analysis of generalization in the XCS classifier system. Evol. Comput. 7(2), 125–149 (1999)
Lanzi, P.L., Loiacono, D., Wilson, S.W., Goldberg, D.E.: XCS with computed prediction in continuous multistep environments. In: IEEE CEC 2005, vol. 3, pp. 2032–2039, September 2005
Lanzi, P.L., Loiacono, D., Wilson, S.W., Goldberg, D.E.: Generalization in the XCSF classifier system: analysis, improvement, and extension. Evol. Comput. 15(2), 133–168 (2007)
Liu, Y., Browne, W.N., Xue, B.: Absumption to complement subsumption in learning classifier systems. In: Proceedings of GECCO 2019, pp. 410–418. ACM, New York, NY, USA (2019)
Liu, Y., Browne, W.N., Xue, B.: Absumption and subsumption based learning classifier systems. In: Proceedings of GECCO 2020, pp. 368–376. ACM, New York, NY, USA (2020)
Pätzel, D., Stein, A., Hähner, J.: A survey of formal theoretical advances regarding XCS. In: Proceedings of GECCO 2019, pp. 1295–1302. Association for Computing Machinery, New York, NY, USA (2019)
Stein, A., Maier, R., Hähner, J.: Toward curious learning classifier systems: combining XCS with active learning concepts. In: Proceedings of GECCO 2017, pp. 1349–1356. ACM, New York, NY, USA (2017)
Stein, A., Maier, R., Rosenbauer, L., Hähner, J.: XCS classifier system with experience replay. In: Proceedings of GECCO 2020, pp. 404–413. ACM, New York, NY, USA (2020)
Stein, A., Menssen, S., Hähner, J.: What about interpolation? A radial basis function approach to classifier prediction modeling in XCSF. In: Proceedings of GECCO 2018, pp. 537–544. ACM, New York, NY, USA (2018)
Stone, C., Bull, L.: For real! XCS with continuous-valued inputs. Evol. Comput. 11(3), 299–336 (2003)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT press (2018)
Urbanowicz, R.J., Moore, J.H.: Learning classifier systems: a complete introduction, review, and roadmap. J. Artif. Evol. App. 2009, 1:1–1:25 (2009)
Urbanowicz, R.J., Moore, J.H.: ExSTraCS 2.0: description and evaluation of a scalable learning classifier system. Evol. Intell. 8(2), 89–116 (2015)
Wilson, S.W.: Generalization in the XCS classifier system. In: Proceedings of GP 1998. Morgan Kaufmann, Madison, Wisconsin, USA (1998)
Wilson, S.W.: Get real! XCS with continuous-valued inputs. In: Lanzi, P.L., Stolzmann, W., Wilson, S.W. (eds.) IWLCS 1999. LNCS (LNAI), vol. 1813, pp. 209–219. Springer, Heidelberg (2000). https://doi.org/10.1007/3-540-45027-0_11
Wilson, S.W.: Classifiers that approximate functions. Nat. Comput. 1(2), 211–234 (2002)
Wilson, S.W.: Classifier fitness based on accuracy. Evol. Comput. 3(2), 149–175 (1995)
Wilson, S.W.: Compact rulesets from XCSI. In: Lanzi, P.L., Stolzmann, W., Wilson, S.W. (eds.) IWLCS 2001. LNCS (LNAI), vol. 2321, pp. 197–208. Springer, Heidelberg (2002). https://doi.org/10.1007/3-540-48104-4_12
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Wagner, A.R.M., Stein, A. (2021). On the Effects of Absumption for XCS with Continuous-Valued Inputs. In: Castillo, P.A., Jiménez Laredo, J.L. (eds) Applications of Evolutionary Computation. EvoApplications 2021. Lecture Notes in Computer Science(), vol 12694. Springer, Cham. https://doi.org/10.1007/978-3-030-72699-7_44
Download citation
DOI: https://doi.org/10.1007/978-3-030-72699-7_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-72698-0
Online ISBN: 978-3-030-72699-7
eBook Packages: Computer ScienceComputer Science (R0)