An Architecture-Altering and Training Methodology for Neural Logic Networks: Application in the banking sector

Athanasios Tsakonas, Georgios Dounias

Abstract

Artificial neural networks have been universally acknowledged for their ability on constructing forecasting and classifying systems. Among their desirable features, it has always been the interpretation of their structure, aiming to provide further knowledge for the domain experts. A number of methodologies have been developed for this reason. One such paradigm is the neural logic networks concept. Neural logic networks have been especially designed in order to enable the interpretation of their structure into a number of simple logical rules and they can be seen as a network representation of a logical rule base. Although powerful by their definition in this context, neural logic networks have performed poorly when used in approaches that required training from data. Standard training methods, such as the back-propagation, require the network’s synapse weight altering, which destroys the network’s interpretability. The methodology in this paper overcomes these problems and proposes an architecture-altering technique, which enables the production of highly antagonistic solutions while preserving any weight-related information. The implementation involves genetic programming using a grammar-guided training approach, in order to provide arbitrarily large and connected neural logic networks. The methodology is tested in a problem from the banking sector with encouraging results.

References

  1. Chia H.W-K., Tan C-L., 2001. Neural logic network learning using genetic programming, Intl. Journal of Comp. Intelligence and Applications, 1:4, pp 357-368
  2. Gruau F., 1994. Neural Network Synthesis using Cellular Encoding and the Genetic Algorithm, Ph.D. Thesis, Ecole Normale Superieure de Lyon, ftp:lip.ens-lyon.fr (140.77.1.11) pub/Rapports/PhD PhD94-01-E.ps.Z
  3. Gruau F., Whitley D., Pyeatt L., 1996. A Comparison between Cellular Encoding and Direct Encoding for Genetic Neural Networks, in Koza J.R., Goldberg D.E., Fogel D.B., Riolo R.L. (eds.), Genetic Programming 1996: Proceedings of the First Annual Conf., pp 81-89, Cambridge, MA, MIT Press
  4. Hussain T., Browse R., 1998. Attribute Grammars for Genetic Representations of Neural Networks and Syntactic Constraints of Genetic Programming, in AIVIGI'98:, Workshop on Evol.Comp., Vancouver BC.
  5. Janikow C.Z., 1996. A Methodology for Processing Problem Constraints in Genetic Programming, in Computers Math.Applic. Vol.32:8,pp 97-113.
  6. Koza J.R., 1992. Genetic Programming: On the Programming of Computers by Means of Natural Selection, Cambridge, MA, MIT Press.
  7. Koza J.R., Keane M.A., Streeter M.J., 2003. Genetic Programming Human-Competitive Results, IEEE Intelligent Systems, May/June 2003, pp 25-31.
  8. Montana D.J., 1995. Strongly Typed Genetic Programming, Evolutionary Computation, vol. .3, no. 2.
  9. Quah T-S., Tan C-L., Teh H-H.,Sriniivasan B., 1995. Utilizing a Neural Logic Expert system in Currency Option Trading, Expert Systems with Applications, 9:2, pp 213-222.
  10. Quah T-S., Tan C-L., Raman K., Sriniivasan B., 1996. Towards integrating rule-based expert systems and neural networks, Decision Support Systems, 17, pp 99-118.
  11. Quinlan, J.R., 1987. Simplifying decision trees. International Journal of Man-Machine Studies, 27, December: pp. 221-234.
  12. Quinlan J.R. 1992. C4.5: Programs for Machine Learning, Morgan Kaufmann.
  13. Ryan C., Collins J.J., O'Neil M. , 1998. Grammatical Evolution: Evolving Programs for an Arbitrary Language, in W.Banzhaf, R.Poli, M.Schoenauer, T.C.Fogarty (Eds.), Genetic Programming, Lecture Notes in Computer Science, Springer.
  14. Statlog 2005. Statlog Use, Test of Australian Credit Scoring data, available online: http://www.liacc.up.pt/ML/statlog/datasets/australian/australian.use.html, date of last access:05/22/05.
  15. Tan A-H., Teow L-N., 1997. Inductive neural logic network and the SCM algorithm, Neurocomputing 14, pp 157-176
  16. Teh H-H., 1995. Neural Logic Networks, World Scientific.
  17. Tsakonas A. Dounias G., 2002. A Scheme for the Evolution of Feedforward Neural Networks using BNF-Grammar Driven Genetic Programming, in Proc. of Annual Workshop of European Network of Excellence on Smart Adaptive Systems 2002, Eunite02, Algarve.
  18. Wong M.L., 2001. A flexible knowledge discovery system using genetic programming and logic grammars, Decision Support Systems, 31, pp 405-428
Download


Paper Citation


in Harvard Style

Tsakonas A. and Dounias G. (2005). An Architecture-Altering and Training Methodology for Neural Logic Networks: Application in the banking sector . In Proceedings of the 1st International Workshop on Artificial Neural Networks and Intelligent Information Processing - Volume 1: ANNIIP, (ICINCO 2005) ISBN 972-8865-36-8, pages 82-93. DOI: 10.5220/0001192100820093


in Bibtex Style

@conference{anniip05,
author={Athanasios Tsakonas and Georgios Dounias},
title={An Architecture-Altering and Training Methodology for Neural Logic Networks: Application in the banking sector},
booktitle={Proceedings of the 1st International Workshop on Artificial Neural Networks and Intelligent Information Processing - Volume 1: ANNIIP, (ICINCO 2005)},
year={2005},
pages={82-93},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001192100820093},
isbn={972-8865-36-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 1st International Workshop on Artificial Neural Networks and Intelligent Information Processing - Volume 1: ANNIIP, (ICINCO 2005)
TI - An Architecture-Altering and Training Methodology for Neural Logic Networks: Application in the banking sector
SN - 972-8865-36-8
AU - Tsakonas A.
AU - Dounias G.
PY - 2005
SP - 82
EP - 93
DO - 10.5220/0001192100820093