Skip to main content
SpringerLink
Log in

Neurules-A Type of Neuro-symbolic Rules: An Overview

  • Conference paper
Book cover Combinations of Intelligent Methods and Applications

Part of the book series: Smart Innovation, Systems and Technologies ((SIST,volume 8))

Abstract

Neurules are a kind of integrated rules integrating neurocomputing and production rules. Each neurule is represented as an adaline unit. Thus, the corresponding neurule base consists of a number of autonomous adaline units (neurules). Due to this fact, a modular and natural knowledge base is constructed, in contrast to existing connectionist knowledge bases. In this paper, we present an overview of our main work involving neurules. We focus on aspects concerning construction of neurules, efficient updates of neurule bases, neurule-based inference and combination of neurules with case-based reasoning. Neurules may be constructed from either symbolic rule bases or empirical data in the form of training examples. Due to the fact that the source knowledge of neurules may change with time, efficient updates of corresponding neurule bases to reflect such changes are performed. Furthermore, the neurule-based inference mechanism is interactive and more efficient than the inference mechanism used in connectionist expert systems. Finally, neurules can be naturally combined with case-based reasoning to provide a more effective representation scheme that exploits multiple knowledge sources and provides enhanced reasoning capabilities.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 129.00
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 169.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 169.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  • Aamodt, A., Plaza, E.: Case-based reasoning: foundational issues, methodological variations and system approaches. AI Communications 7, 39–59 (1994)

    Google Scholar 

  • Andrews, R., Diederich, J., Tickle, A.: A survey and critique of techniques for extracting rules from trained artificial neural networks. Knowledge-Based Systems 8, 373–389 (1995)

    Article  Google Scholar 

  • Bader, S., Hitzler, P.: Dimensions of neural-symbolic integration – a structured survey. In: Artemov, S., Barringer, H., d’Avila Garcez, A.S., Lamb, L.C., Woods, J. (eds.) We Will Show Them: Essays in Honour of Dov Gabbay. International Federation for Computational Logic, vol. 1, pp. 167–194. College Publications (2005)

    Google Scholar 

  • Bader, S., Hitzler, P.: Holldobler Connectionist model generation: a first-order approach. Neurocomputing 71, 2420–2432 (2008)

    Article  Google Scholar 

  • Bookman, L., Sun, R. (eds.): Special issue on integrating neural and symbolic processes. Connection Science, vol. 5(3-4) (1993)

    Google Scholar 

  • Browne, A., Sun, R.: Connectionist inference models. Neural Networks 14, 1331–1355 (2001)

    Article  Google Scholar 

  • Cloete, I., Zurada, J.M. (eds.): Knowledge-based neurocomputing. The MIT Press, Cambridge (2000)

    Google Scholar 

  • Frank, A., Asuncion, A.: UCI Machine Learning Repository, School of Information and Computer Science, University of California, Irvina, CA (2010), http://archive.ics.uci.edu/ml (accessed October 9, 2010)

  • Fu, L.M.: Knowledge-based connectionism for revising domain theories. IEEE Transactions on Systems, Man, and Cybernetics 23, 173–182 (1993)

    Article  Google Scholar 

  • Fu, L.M. (ed.): Proceedings of the International Symposium on Integrating Knowledge and Neural Heuristics. Pensacola, Florida (1994)

    Google Scholar 

  • Gallant, S.I.: Connectionist expert systems. Communications of the ACM 31, 152–169 (1988)

    Article  Google Scholar 

  • Gallant, S.I.: Neural network learning and expert systems. The MIT Press, Cambridge (1993)

    MATH  Google Scholar 

  • d’Avila Garcez, A.S., Broda, K., Gabbay, D.M.: Neural-symbolic learning systems: foundations and applications. In: Perspectives in Neural Computing. Springer, Heidelberg (2002)

    Google Scholar 

  • d’Avila Garcez, A., Gabbay, D., Holldobler, S., Taylor, J.: Special issue on neural-symbolic systems. Journal of Applied Logic 2 (2004)

    Google Scholar 

  • d’Avila Garcez, A., Lamb, L.C., Gabbay, D.M.: Connectionist modal logic: representing modalities in neural networks. Theoretical Computer Science 371, 34–53 (2007)

    Article  MATH  MathSciNet  Google Scholar 

  • Ghalwash, A.Z.: A recency inference engine for connectionist knowledge bases. Applied Intelligence 9, 201–215 (1998)

    Article  Google Scholar 

  • Golding, A.R., Rosenbloom, P.S.: Improving accuracy by combining rule-based and case-based reasoning. Artificial Intelligence 87, 215–254 (1996)

    Article  Google Scholar 

  • Gonzalez, A., Dankel, D.: The engineering of knowledge-based systems: theory and practice. Prentice-Hall, Upper Saddle River (1993)

    MATH  Google Scholar 

  • Hatzilygeroudis, I., Prentzas, J.: Neurules: integrating symbolic rules and neurocomputting. In: Fotiades, D., Nikolopoulos, S. (eds.) Advances in Informatics. World Scientific Publishing, Singapore (2000a)

    Google Scholar 

  • Hatzilygeroudis, I., Prentzas, J.: Neurules: improving the performance of symbolic rules. International Journal on AI Tools 9, 113–130 (2000b)

    Article  Google Scholar 

  • Hatzilygeroudis, I., Prentzas, J.: An efficient hybrid rule based inference engine with explanation capability. In: Kolen, J., Russell, I. (eds.) Proceedings of the Fourteenth International Florida Artificial Intelligence Research Society Conference. AAAI Press, Menlo Park (2001a)

    Google Scholar 

  • Hatzilygeroudis, I., Prentzas, J.: Constructing modular hybrid knowledge bases for expert systems. International Journal on AI Tools 10, 87–105 (2001b)

    Article  Google Scholar 

  • Hatzilygeroudis, I., Prentzas, J.: Neuro-symbolic approaches for knowledge representation in expert systems. International Journal on Hybrid Intelligent Systems 1, 111–126 (2004a)

    MATH  Google Scholar 

  • Hatzilygeroudis, I., Prentzas, J.: Using a hybrid rule-based approach in developing an intelligent tutoring system with knowledge acquisition and update capabilities. Expert Systems with Applications 26, 477–492 (2004b)

    Article  Google Scholar 

  • Hatzilygeroudis, I., Prentzas, J.: Integrating (rules, neural networks) and cases for knowledge representation and reasoning in expert systems. Expert Systems with Applications 27, 63–75 (2004c)

    Article  Google Scholar 

  • Hatzilygeroudis, I., Prentzas, J.: Knowledge representation requirements for intelligent tutoring systems. In: Lester, J.C., Vicari, R.M., Paraguaçu, F. (eds.) ITS 2004. LNCS, vol. 3220, pp. 87–97. Springer, Heidelberg (2004d)

    Chapter  Google Scholar 

  • Hatzilygeroudis, I., Prentzas, J.: Knowledge representation in intelligent educational systems. In: Ma, Z. (ed.) Web-based intelligent e-learning systems: technologies and applications. Idea Group Inc., Hershey (2006)

    Google Scholar 

  • Hatzilygeroudis, I., Prentzas, J.: Integrated rule-based learning and inference. IEEE Transactions on Knowledge and Data Engineering 22, 1549–1562 (2010)

    Article  Google Scholar 

  • Haykin, S.: Neural Networks and Learning Machines. Prentice Hall, Upper Saddle River (2008)

    Google Scholar 

  • Hilario, M.: An overview of strategies for neurosymbolic integration. In: Sun, R., Alexandre, E. (eds.) Connectionist-symbolic integration: from unified to hybrid approaches. Lawrence Erlbaum Associates, Mahwah (1997)

    Google Scholar 

  • Holldobler, S., Kalinke, Y.: Towards a massively parallel computational model for logic programming. In: Proceedings of ECAI 1994 Workshop on Combining Symbolic and Connectionist Processing. pp. 68–77. ECCAI (1994)

    Google Scholar 

  • Komendantskaya, E., Lane, M., Seda, A.K.: Connectionist representation of multi-valued logic programs. In: Hammer, B., Hitzler, P. (eds.) Perspectives of Neural-Symbolic Integration. Springer, Heidelberg (2007)

    Google Scholar 

  • McGarry, K., Wermter, S., MacIntyre, J.: Hybrid neural systems: from simple coupling to fully integrated neural networks. Neural Computing Surveys 2, 62–93 (1999)

    Google Scholar 

  • Medsker, L.R.: Hybrid intelligent systems. Kluwer Academic Publishers, Dordrecht (1995)

    MATH  Google Scholar 

  • Prentzas, J., Hatzilygeroudis, I.: Integrating hybrid rule-based with case-based reasoning. In: Craw, S., Preece, A.D. (eds.) ECCBR 2002. LNCS (LNAI), vol. 2416, p. 336. Springer, Heidelberg (2002)

    Chapter  Google Scholar 

  • Prentzas, J., Hatzilygeroudis, I., Garofalakis, J.: A web-based intelligent tutoring system using hybrid rules as its representational basis. In: Cerri, S.A., Gouardéres, G., Paraguaçu, F. (eds.) ITS 2002. LNCS, vol. 2363, p. 119. Springer, Heidelberg (2002)

    Chapter  Google Scholar 

  • Prentzas, J., Hatzilygeroudis, I.: Rule-based update methods for a hybrid rule base. Data and Knowledge Engineering 55, 103–128 (2005)

    Article  Google Scholar 

  • Prentzas, J., Hatzilygeroudis, I.: Construction of neurules from training examples: a thorough investigation. In: Garcez, A., Hitzler, P., Tamburini, G. (eds.) Proceedings of the ECAI 2006 Workshop on Neural-Symbolic Learning and Reasoning (2006)

    Google Scholar 

  • Prentzas, J., Hatzilygeroudis, I.: Categorizing approaches combining rule-based and case-based reasoning. Expert Systems 24, 97–122 (2007a)

    Article  Google Scholar 

  • Prentzas, J., Hatzilygeroudis, I.: Incrementally updating a hybrid rule base based on empirical data. Expert Systems 24, 212–231 (2007b)

    Article  Google Scholar 

  • Prentzas, J., Hatzilygeroudis, I.: Combinations of case-based reasoning with other intelligent methods. International Journal of Hybrid Intelligent Systems 6, 189–209 (2009)

    MATH  Google Scholar 

  • Reichgelt, H.: Knowledge representation, an AI perspective. Ablex, New York (1991)

    Google Scholar 

  • Souici-Meslati, L., Sellami, M.: Toward a generalization of neuro-symbolic recognition: an application to Arabic words. International Journal of Knowledge-based and Intelligent Engineering Systems 10, 347–361 (2006)

    Google Scholar 

  • Sun, R., Alexandre, E. (eds.): Connectionist-symbolic integration: from unified to hybrid approaches. Lawrence Erlbaum Associates, Mahwah (1997)

    Google Scholar 

  • Teng, T.-H., Tan, Z.-M., Tan, A.-H.: Self-organizing neural models integrating rules and reinforcement learning. In: Proceedings of the IEEE International Joint Conference on Neural Networks, IEEE, Los Alamitos (2008)

    Google Scholar 

  • Towell, G., Shavlik, J.: Knowledge-based artificial neural networks. Artificial Intelligence 70, 119–165 (1994)

    Article  MATH  Google Scholar 

  • Wermter, S., Sun, R. (eds.): Hybrid neural systems. Springer, Heidelberg (2000)

    Google Scholar 

  • Xianyu, J.C., Juan, Z.C., Gao, L.J.: Knowledge-based neural networks and its application in discrete choice analysis. In: Proceedings of the Fourth International Conference on Networked Computing and Advanced Information Management. IEEE Computer Society Press, Los Alamitos (2008)

    Google Scholar 

  • Yu, L., Wang, L., Yu, J.: Identification of product definition patterns in mass customization using a learning-based hybrid approach. International Journal of Advanced Manufacturing Technologies 38, 1061–1074 (2008)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Education Sciences, Dept. of Education Sciences in Pre-School Age, Democritus University of Thrace, Nea Chili, 68100, Alexandroupolis, Greece

    Jim Prentzas

  2. School of Engineering, Dept. of Computer Engineering and Informatics, University of Patras, 26500, Patras, Greece

    Ioannis Hatzilygeroudis

Authors
  1. Jim Prentzas
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ioannis Hatzilygeroudis
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Graphics, Multimedia & GIS Lab Department of Computer Engineering & Informatics , University of Patras, 26500, Patras, Hellas, Greece

    Ioannis Hatzilygeroudis

  2. Dept. of Education Sciences in Pre-School Age, Democritus University of Thrace School of Education Sciences, 68100, Nea Chili, Alexandroupolis, Greece

    Jim Prentzas

Rights and permissions

Reprints and permissions

Copyright information

© 2011 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Prentzas, J., Hatzilygeroudis, I. (2011). Neurules-A Type of Neuro-symbolic Rules: An Overview. In: Hatzilygeroudis, I., Prentzas, J. (eds) Combinations of Intelligent Methods and Applications. Smart Innovation, Systems and Technologies, vol 8. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-19618-8_9

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-19618-8_9

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-19617-1

  • Online ISBN: 978-3-642-19618-8

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics

Search

Navigation