This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Integrated Rule-Based Learning and Inference
November 2010 (vol. 22 no. 11)
pp. 1549-1562
ASCII Text
x 
 
Ioannis Hatzilygeroudis, Jim Prentzas, "Integrated Rule-Based Learning and Inference," IEEE Transactions on Knowledge and Data Engineering, vol. 22, no. 11, pp. 1549-1562, November, 2010.
 
 
BibTex
x
 
@article{ 10.1109/TKDE.2010.79,
author = {Ioannis Hatzilygeroudis and Jim Prentzas},
title = {Integrated Rule-Based Learning and Inference},
journal ={IEEE Transactions on Knowledge and Data Engineering},
volume = {22},
number = {11},
issn = {1041-4347},
year = {2010},
pages = {1549-1562},
doi = {http://doi.ieeecomputersociety.org/10.1109/TKDE.2010.79},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - JOUR
JO - IEEE Transactions on Knowledge and Data Engineering
TI - Integrated Rule-Based Learning and Inference
IS - 11
SN - 1041-4347
SP1549
EP1562
EPD - 1549-1562
A1 - Ioannis Hatzilygeroudis,
A1 - Jim Prentzas,
PY - 2010
KW - Neurosymbolic integration
KW - integrated inference
KW - rule-based reasoning
KW - neurocomputing.
VL - 22
JA - IEEE Transactions on Knowledge and Data Engineering
ER -
 
Ioannis Hatzilygeroudis, University of Patras, Patras
Jim Prentzas, Democritus University of Thrace, Alexandroupolis
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). In this paper, we present the construction process and the inference mechanism of neurules and explore their generalization capabilities. The construction process, which also implements corresponding learning algorithm, creates neurules from a given empirical data set. The inference mechanism of neurules is integrated in its nature; it combines neurocomputing with symbolic processes. It is also interactive, i.e., it interacts with the user asking him/her to provide values for some variables necessary to carry on inference. As shown via experiments, the neurules' integrated inference mechanism is more efficient than the inference mechanism used in connectionist expert systems. Furthermore, neurules generalize much better than their constituent neural component (adaline unit) and are comparable to the backpropagation neural net (BPNN).

[1] A. Asuncion and D.J. Newman, "UCI Machine Learning Repository," http://www.ics.uci.edu/~mlearnMLRepository.html , School of Information and Computer Science, Univ. of California, 2007.
[2] S. Bader and P. Hitzler, "Dimensions of Neural-Symbolic Integration—A Structured Survey," We Will Show Them: Essays in Honour of Dov Gabbay, S. Artemov, H. Barringer, A.S. d'Avila Garcez, L.C. Lamb, and J. Woods, eds., vol. 1, pp. 167-194, College Publications, 2005.
[3] S. Bader, P. Hitzler, S. Holldobler, and A. Witzel, "A Fully Connectionist Model Generator for Covered First-Order Logic Programs," Proc. 20th Int'l Joint Conf. Artificial Intelligence (IJCAI '07), pp. 666-671, 2007.
[4] S. Bader, P. Hitzler, and S. Holldobler, "Connectionist Model Generation: A First-Order Approach," Neurocomputing, vol. 71, pp. 2420-2432, 2008.
[5] M. Bohanec and B. Zupan, "AI Lab Data Sets," http://magix.fri.uni-lj.si/blaz/hintdata sets.htm , Faculty of Computer and Information Science, Univ. of Ljubljana, 1997.
[6] G. Bologna, "A Model for Single and Multiple Knowledge Based Networks," Artificial Intelligence in Medicine, vol. 28, no. 2, pp. 141-163, 2003.
[7] Connection Science, special issue on integrating neural and symbolic processes, L. Bookman and R. Sun, eds., vol. 5, nos. 3/4, 1993.
[8] A. Browne and R. Sun, "Connectionist Inference Models," Neural Networks, vol. 14, no. 10, pp. 1331-1355, 2001.
[9] G.A. Carpenter and A.-H. Tan, "Rule Extraction: From Neural Architecture to Symbolic Representation," Connection Science, vol. 7, pp. 3-27, 1995.
[10] Knowledge-Based Neurocomputing, I. Cloete and J.M. Zurada, eds. MIT Press, 2000.
[11] L.M. Fu, "Knowledge-Based Connectionism for Revising Domain Theories," IEEE Trans. Systems, Man, and Cybernetics, vol. 23, no. 1, pp. 173-182, Jan./Feb. 1993.
[12] S.I. Gallant, "Connectionist Expert Systems," Comm. ACM, vol. 31, no. 2, pp. 152-169, 1988.
[13] S.I. Gallant, Neural Network Learning and Expert Systems. MIT Press, 1993.
[14] A.S. d'Avila Garcez, K. Broda, and D.M. Gabbay, "Symbolic Knowledge Extraction from Trained Neural Networks: A Sound Approach," Artificial Intelligence, vol. 125, nos. 1/2, pp. 155-207, 2001.
[15] A. d'Avila Garcez, K. Broda, and D.M. Gabbay, Neural-Symbolic Learning Systems: Foundations and Applications, Perspectives in Neural Computing. Springer-Verlag, 2002.
[16] A. d'Avila Garcez, D. Gabbay, S. Holldobler, and J. Taylor, J. Applied Logic, special issue on neural-symbolic systems, vol. 2, no. 3, 2004.
[17] A. d'Avila Garcez and L.C. Lamb, "A Connectionist Computational Model for Epistemic and Temporal Reasoning," Neural Computation, vol. 18, no. 7, pp. 1711-1738, 2006.
[18] A. d'Avila Garcez, L.C. Lamb, and D.M. Gabbay, "Connectionist Computations of Intuitionistic Reasoning," Theoretical Computer Science, vol. 358, no. 1, pp. 34-55, 2006.
[19] A. d'Avila Garcez, L.C. Lamb, and D.M. Gabbay, "Connectionist Modal Logic: Representing Modalities in Neural Networks," Theoretical Computer Science, vol. 371, nos. 1/2, pp. 34-53, 2007.
[20] A. d'Avila Garcez, L.C. Lamb, and D.M. Gabbay, Neural-Symbolic Cognitive Reasoning. Springer-Verlag, 2008.
[21] A.Z. Ghalwash, "A Recency Inference Engine for Connectionist Knowledge Bases," Applied Intelligence, vol. 9, no. 3, pp. 201-215, 1998.
[22] H. Gust, K.-U. Kuhngerger, and P. Geibel, "Learning Models of Predicate Logical Theories with Neural Networks Based on Topos Theory," Perspectives of Neural-Symbolic Integration, vol. 23, pp. 233-264, Springer-Verlag, 2007.
[23] Perspectives of Neural-Symbolic Integration, B. Hammer and P. Hitzler, eds. Springer-Verlag, 2007.
[24] I. Hatzilygeroudis and J. Prentzas, "Neurules: Improving the Performance of Symbolic Rules," Int'l J. AI Tools (IJAIT), vol. 9, no. 1, pp. 113-130, 2000.
[25] I. Hatzilygeroudis and J. Prentzas, "Constructing Modular Hybrid Knowledge Bases for Expert Systems," Int'l J. AI Tools (IJAIT), vol. 10, nos. 1/2, pp. 87-105, 2001.
[26] I. Hatzilygeroudis and J. Prentzas, "An Efficient Hybrid Rule Based Inference Engine with Explanation Capability," Proc. 14th Int'l FLAIRS Conf., pp. 227-231, 2001.
[27] I. Hatzilygeroudis and J. Prentzas, "Neuro-Symbolic Approaches for Knowledge Representation in Expert Systems," Int'l J. Hybrid Systems (IJHIS), vol. 1, nos. 3/4, pp. 111-126, 2004.
[28] I. Hatzilygeroudis and J. Prentzas, "Using a Hybrid Rule-Based Approach in Developing an Intelligent Tutoring System with Knowledge Acquisition and Update Capabilities," J. Expert Systems with Applications, vol. 26, no. 4, pp. 477-492, 2004.
[29] M. Hilario, "An Overview of Strategies for Neurosymbolic Integration," Connectionist-Symbolic Integration: From Unified to Hybrid Approaches, R. Sun and E. Alexandre, eds., Lawrence Erlbaum, 1997.
[30] M. Hilario and A. Rida, "The Use of Prior Knowledge in Neural Network Configuration and Training," Biological and Artificial Computation: From Neuroscience to Technology, pp. 227-236, Springer, 1997.
[31] S. Holldobler and Y. Kalinke, "Towards a Massively Parallel Computational Model for Logic Programming," Proc. ECAI94 Workshop Combining Symbolic and Connectionist Processing (ECCAI '94), pp. 68-77, 1994.
[32] S. Holldobler, Y. Kalinke, and H.-P. Storr, "Approximating the Semantics of Logic Programs by Recurrent Neural Networks," Applied Intelligence, vol. 11, no. 1, pp. 45-58, 1999.
[33] E. Komendantskaya, M. Lane, and A.K. Seda, "Connectionist Representation of Multi-Valued Logic Programs," Perspectives of Neural-Symbolic Integration, pp. 283-313, Springer, 2007.
[34] L.C. Lamb, R.V. Borges, and A. d'Avila Garcez, "A Connectionist Cognitive Model for Temporal Synchronisation and Learning," Proc. 22nd Conf. Artificial Intelligence (AAAI '07), pp. 827-832, 2007.
[35] J.J. Mahoney and R. Mooney, "Combining Connectionist and Symbolic Learning to Refine Certainty-Factor Rule Bases," Connection Science, vol. 5, nos. 3/4, pp. 339-364, 1993.
[36] K. McGarry, S. Wermter, and J. MacIntyre, "Hybrid Neural Systems: From Simple Coupling to Fully Integrated Neural Networks," Neural Computing Surveys, vol. 2, pp. 62-93, 1999.
[37] L.R. Medsker, Hybrid Intelligent Systems, second printing. Kluwer Academic Publishers, 1998.
[38] L. Souici-Meslati and M. Sellami, "Toward a Generalization of Neuro-Symbolic Recognition: An Application to Arabic Words," Int'l J. Knowledge-Based and Intelligent Eng. Systems, vol. 10, no. 5, pp. 347-361, 2006.
[39] C.W. Omlin and C.L. Giles, "Rule Revision with Recurrent Neural Networks," IEEE Trans. Knowledge and Data Eng., vol. 8, no. 1, pp. 183-188, Feb. 1996.
[40] T.R. Payne and P. Edwards, "Implicit Feature Selection with the Value Difference Metric," Proc. 13th European Conf. Artificial Intelligence, Henri Prade, ed., pp. 450-454, 1998.
[41] J. Prentzas and I. Hatzilygeroudis, "Construction of Neurules from Training Examples: A Thorough Investigation," Proc. ECAI-06 Workshop "Neural-Symbolic Learning and Reasoning" (NeSy '06), A. Garcez, P. Hitzler, and G. Tamburini, eds., pp. 35-40, Aug./Sept. 2006.
[42] H. Reichgelt, Knowledge Representation: An AI Perspective. Ablex, 1991.
[43] L. Shastri, "SHRUTI: A Neurally Motivated Architecture for Rapid, Scalable Inference," Perspectives of Neural-Symbolic Integration, pp. 183-203, Springer, 2007.
[44] J. Sima, "Neural Expert Systems," Neural Networks, vol. 8, no. 2, pp. 261-271, 1995.
[45] J. Sima and J. Cervenka, "Neural Knowledge Processing in Expert Systems," Knowledge-Based Neurocomputing, I. Cloete and J.M. Zurada, eds., pp. 419-466, The MIT Press, 2000.
[46] A.-H. Tan, "Cascade ARTMAP: Integrating Neural Computation and Symbolic Knowledge Processing," IEEE Trans. Neural Networks, vol. 8, no. 2, pp. 237-250, 1997.
[47] T.-H. Teng, Z.-M. Tan, and A.-H. Tan, "Self-Organizing Neural Models Integrating Rules and Reinforcement Learning," Proc. IEEE Int'l Joint Conf. Neural Networks, pp. 3771-3778, 2008.
[48] H. Tirri, "Replacing the Pattern Matcher of an Expert System with a Neural Network," Intelligent Hybrid Systems, S. Goonatilake and K. Sukdev, eds., John Wiley & Sons, 1995.
[49] G. Towell and J. Shavlik, "Extracting Refined Rules from Knowledge-Based Neural Networks," Machine Learning, vol. 13, no. 1, pp. 71-101, 1993.
[50] G. Towell and J. Shavlik, "Knowledge-Based Artificial Neural Networks," Artificial Intelligence, vol. 70, nos. 1/2, pp. 119-165, 1994.
[51] Hybrid Neural Systems, S. Wermter and R. Sun, eds. Springer-Verlag, 2000.
[52] J.C. Xianyu, Z.C. Juan, and L.J. Gao, "Knowledge-Based Neural Networks and Its Application in Discrete Choice Analysis," Proc. Fourth Int'l Conf. Networked Computing and Advanced Information Management, pp. 491-496, 2008.
[53] J. Yu, L. Xi, and X. Zhou, "Intelligent Monitoring and Diagnosis of Manufacturing Processes Using an Integrated Approach of KBANN and GA," Computers in Industry, vol. 59, no. 5, pp. 489-501, 2008.
[54] L. Yu, L. Wang, and J. Yu, "Identification of Product Definition Patterns in Mass Customization Using a Learning-Based Hybrid Approach," Int'l J. Advanced Manufacturing Technologies, vol. 38, nos. 11/12, pp. 1061-1074, 2008.

Index Terms:
Neurosymbolic integration, integrated inference, rule-based reasoning, neurocomputing.
Citation:
Ioannis Hatzilygeroudis, Jim Prentzas, "Integrated Rule-Based Learning and Inference," IEEE Transactions on Knowledge and Data Engineering, vol. 22, no. 11, pp. 1549-1562, Nov. 2010, doi:10.1109/TKDE.2010.79
Usage of this product signifies your acceptance of the Terms of Use.