Summary
This chapter presents Petri net models for two forms of rough neural computing: training set production and approximate reasoning schemes (AR schemes) defined in the context of parameterized approximation spaces. The focus of the first form of rough-neural computing is inductive learning and the production of training (optimal feature set selection), using knowledge reduction algorithms. This first form of neural computing can be important in designing neural networks defined in the context of parameterized approximation spaces. A high-level Petri net model of a neural network classifier with an optimal feature selection procedure in its front end is given. This model is followed by the development of a number of Petri net models of what are known as elementary approximation neurons (EA neurons). The design of an EA neuron includes an uncertainty function that constructs a granule approximation and a rough inclusion (threshold activation) function that measures the degree to which granule approximation is part of a target granule. The output of an EA neuron is an elementary granule. There are many forms of elementary granules (e.g., conjunction of descriptors, rough inclusion function value). Each of the EA neurons considered in this chapter output a rough inclusion function value. An EA neuron can be designed so that it is trainable, that is, a feedback loop can be included in the design of the EA neuron so that one or more approximation space parameters can be tuned to improve the performance of the neuron. The design of three sample EA neurons is given. One of these neurons behaves like a high-pass filter.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
Reference
M.A. Arbib. The artificial neuron. In E. Fiesler, R. Beale, editorsHandbook of Neural ComputationB 1.7, Institute of Physics, Bristol, 1997.
I.M. Bochenski. AHistory of Formal Logic. Chelsea, New York, 1956.
B. Chakraborty. Feature subset selection by neuro-rough hybridization. In W. Ziarko, Y. Yao, editorsProceedings of the Second International Conference on Rough Sets and Current Trends in Computing (RSCTC 2000)LNAI 2005, 519–526, Springer, Berlin, 2001.
D.L. Dill.Trace Theory for Automatic Hierarchical Verification of Speed-Independent Circuits.MIT Press, Cambridge MA, 1989.
Bonabeau et al.Swarm Intelligence: From Natural to Artificial Systems.Oxford University Press, Oxford, 2000.
L. Han, J.F. Peters, S. Ramanna, R. Zhai. Classifying faults in high voltage power systems: A rough-fuzzy neural computational approach. In N. Zhong, A. Skowron, S. Ohsuga, editorsNew Directions in Rough Sets Data Mining and Granular-Soft ComputingLNAI 1711, 47–54, Springer, Berlin, 1999.
K. Jensen.Coloured Petri Nets—Basic Concepts Analysis Methods and Practical UseVol. 1. Springer, Berlin, 1992.
T. Kohonen. The self-organizing map.Proceedings of the IEEE78: 1464–1480, 1999.
J. Komorowski, Z. Pawlak, L. Polkowski, A. Skowron. Rough sets: A tutorial. In S.K. Pal, A. Skowron, editorsRough Fuzzy Hybridization: A New Trend in Decision-Making3–98, Springer, Singapore, 1999.
P.J. Lingras. Comparison of neofuzzy and rough neural networks.Information Sciences110: 207–215, 1998.
P.J. Lingras. Fuzzy-rough and rough-fuzzy serial combinations in neurocomputing.Neurocomputing: An International Journal36: 29–44, 2001.
R. Milner.Calculus of Communicating Systems.Report number ECS-LFCS-86–7 of Computer Science Department, University of Edinburgh, Edinburgh, 1986.
R. MilnerCommunication and Concurrency.Prentice-Hall, New York, 1989.
S. Mitra, P. Mitra, S.K. Pal. Evolutionary modular design of rough knowledge-based network with fuzzy attributes.Neurocomputing: An International Journal36: 45–66, 2001.
S. K. Pal, S. Mitra. Multi-layer perceptron, fuzzy sets and classification.IEEE Transactions on Neural Networks3: 683–697, 1992.
Z. Pawlak.Rough Sets: Theoretical Aspects of Reasoning About Data.Kluwer, Dordrecht, 1991.
Z. Pawlak, J.F. Peters, A. Skowron, Z. Suraj, S. Ramanna, M. Borkowski. Rough measures: Theory and applications. In S. Hirano, M. Inuiguchi, S. Tsumoto, editorsRough Set Theory and Granular ComputingVol. 5(1/2) of Bulletin of the International Rough Set Society, 177–184, 2001.
Z. Pawlak, A. Skowron. Rough membership functions. In R. Yager, M. Fedrizzi, J. Kacprzyk, editorsAdvances in the Dempster—Shafer Theory of Evidence251–271, Wiley, New York, 1994.
W. Pedrycz, L. Han, J.F. Peters, S. Ramanna, R. Zhai. Calibration of software quality: Fuzzy neural and rough neural computing approaches.Neurocomputing: An International Journal36: 149–170, 2001.
J.F. Peters, L. Han, S. Ramanna. Rough neural computing in signal analysis.Computational Intelligence17(3): 493–513, 2001.
J.F. Peters, S. Ramanna. A rough set approach to assessing software quality: Concepts and rough Petri net model. In S.K. Pal, A. Skowron, editorsRough Fuzzy Hybridization: A New Trend in Decision-Making349–380, Springer, Berlin, 1999.
J.F. Peters, S. Ramanna, M. Borkowski, A. Skowron, Z. Suraj. Sensor, filter and fusion models with rough Petri nets.Fundamenta Informaticae47: 307–323, 2001.
A. Skowron, J. Stepaniuk. Information granule decomposition.Fundamenta Informaticae47(3/4): 337–350, 2001.
J.F. Peters, A. Skowron, Z. Suraj, S. Ramanna. Guarded transitions in rough Petri nets. InProceedings of the 7th European Congress on Intelligent Systems and Soft Computing (EUFIT’99)203–212, Verlag Mainz, Aachen, 1999.
C.A. Petri.Kommunikation mit Automaten.Institut für Instrumentelle Mathematik, Schriften des IIM Nr.3, Bonn, 1962.
L. Polkowski, A. Skowron. Rough mereological calculi of granules: A rough set approach to computation.Computational Intelligence17(3): 472–492, 2001.
L. Polkowski, A. Skowron. Rough mereology. InProceedings of the International Symposium on Methodology for Intelligent Systems (ISMIS’94)LNAI 869, 85–94, Springer, Berlin, 1994.
L. Polkowski, A. Skowron. Rough-neuro computing. In W. Ziarko and Y. Yao, editorsProceedings of the Second International Conference on Rough Sets and Current Trends in Computing (RSCTC 2000)LNAI 2005, 57–64, Springer, Berlin, 2001.
A. Skowron. Toward intelligent systems: Calculi of information granules.Bulletin of the International Rough Set Society5: 9–30, 2001.
A. Skowron, C. Rauszer. The discernibility matrices and functions in information systems. In R. Slowiñski, editorIntelligent Decision Support: Handbook of Applications and Advances of the Rough Sets Theory331–362, Kluwer, Dordrecht, 1992.
A. Skowron, J. Stepaniuk. Decision rules based on discernibility matrices and decision matrices. InProceedings of the 3rd International Workshop on Rough Sets and Soft Computing (RSSC’94)602–609, San Jose, CA, 1994.
A. Skowron, J. Stepaniuk. Information granules in distributed environment. In N. Zhong, A. Skowron, S. Ohsuga, editorsProceedings of the 3rd International Workshop on Rough Sets Data Mining and Granular-Soft Computing (RSFDGrC’99)LNAI 1711, 357–365, Springer, Berlin, 1999.
A. Skowron, J. Stepaniuk. Information granules: Towards foundations of granular computing.International Journal of Intelligent Systems16: 57–1044, 2001.
A. Skowron, J. Stepaniuk, J.F. Peters. Extracting patterns using information granules.Bulletin International Rough Set Society5: 135–142,2001.
A. Skowron, J. Stepaniuk, J.F. Peters. Hierarchy of information granules. In L. Czaja, editorProceedings of the Workshop on Concurrency Specification and Programming (CSP 2001)254–268, Warsaw, Poland, 2001.
R.W. Swiniarski.RoughNeuralLab software package.Developed at San Diego State University, San Diego, CA, 1995.
R.W. Swiniarski, L. Hargis. Rough sets as a front end of neural networks texture classifiers.Neurocomputing: An International Journal36: 85–103, 2001.
R.W. Swiniarski, A. Skowron. Rough set methods in feature selection and recognition.Pattern Recognition Letters24(6): 833–849, 2003.
M.S. Szczuka. Rough sets and artificial neural networks. In L. Polkowski, A. Skowron, editorsRough Sets in Knowledge Discovery 2: Applications Cases Studies and Software Systems449–470, Physica, Heidelberg, 1998.
P. Wojdyllo. Wavelets, rough sets and artificial neural networks in EEG analysis. InProceedings of the 1st International Conference on Rough Sets and Current Trends in Computing (RSCTC’98)LNAI 1424, 444–449, Springer, Berlin, 1998.
L.A. Zadeh. Fuzzy logic = computing with words.IEEE Transactions on Fuzzy Systems4: 103–111, 1996.
L.A. Zadeh. The key roles of information granulation and fuzzy logic in human reasoning, concept formulation and computing with words. InProceedings of the 5th International Conference on Fuzzy Systems (FUZZ-IEEE’96)8–11, New Orleans, LA, 1996.
N. Zhong, A. Skowron, S. Ohsuga, editors.Proceedings of the 3rd International Workshop on New Directions in Rough Sets Data Mining and Granular Soft Computing (RSFDGrC’99)LNAI 1711, Springer, Berlin, 1999.
W. Ziarko, Y.Y. Yao, editors.Proceedings of the International Conference on Rough Sets and Current Trends in Computing (RSCTC 2000), LNAI 2005Springer, Berlin, 2001.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Peters, J.F., Ramanna, S., Suraj, Z., Borkowski, M. (2004). Rough Neurons: Petri Net Models and Applications. In: Pal, S.K., Polkowski, L., Skowron, A. (eds) Rough-Neural Computing. Cognitive Technologies. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-18859-6_18
Download citation
DOI: https://doi.org/10.1007/978-3-642-18859-6_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-62328-8
Online ISBN: 978-3-642-18859-6
eBook Packages: Springer Book Archive