Summary
This chapter presents a new paradigm for neural computing that has its roots in rough set theory. Historically, this paradigm has three main threads: production of a training set description, calculus of granules, and interval analysis. This paradigm gains its inspiration from the work of Pawlak on rough set philosophy as a basis for machine learning and from work on data mining and pattern recognition by Swiniarski and others in the early 1990s. The focus of this work is on the production of a training set description and inductive learning using knowledge reduction algorithms. This first thread in rough-neural computing has a strong presence in current neural computing research. The second thread in rough-neural computing has two main components: information granule construction in distributed systems of agents and local parameterized approximation spaces (see Sect. 2.2 and Chap. 3). A formal treatment of the hierarchy of relations of being a part to a degree (also known as approximate rough mereology) was introduced by Polkow ski and Skowron in the mid-and late-1990s. Approximate rough mereology provides a basis for an agent-based, adaptive calculus of granules. This calculus serves as a guide in designing rough-neural computing systems. A number of touchstones of rough-neural computing have emerged from efforts to establish the foundations for granular computing: cooperating agent, granule, granule measures (e.g., inclusion, closeness), and approximation space parameter calibration. The notion of a cooperating agent in a distributed system of agents provides a model for a neuron. Information granulation and granule approximation define two principal activities of a neuron. Included in the toolbox of an agent (neuron) are measures of granule inclusion and closeness of granules.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Reference
M.A. Arbib. The artificial neuron. In E. Fiesler, R. Beale, editorsHandbook of Neural ComputationB1.1-B1.7, Institute of Physics Publishing, Bristol, 1997.
M. Banerjee, S. Mitra, S.K. Pal. Rough fuzzy MLP: Knowledge encoding and classification.IEEE Transactions on Neural Networks9(6): 1203–1216, 1998.
I.M. Bocheñski.A History of Formal Logic.Chelsea, New York, 1956.
E. Bonabeau, M. Dongo, G. Theraulaz.Swarm Intelligence: From Natural to Artificial Systems. Oxford University Press, Oxford, 2000.
B. Chakraborty. Feature subset selection by neuro-rough hybridization. In[74]519–572, 2001.
N.E. Fenton, S.L. Pfleeger.Software Metrics: A Rigorous & Practical Approach.PWS, Boston, 1997.
W. Gellert, H. Kustner, M. Hellwich, H. Kastner.The VNR Concise Encyclopedia of Mathematics.Van Nostrand, London, 1975.
P.R. Halmos.Measure Theory.Van Nostrand, London, 1950.
L. Han, R. Menzies, J.F. Peters, L. Crowe. High voltage power fault-detection and analysis system: Design and implementation. InProceedings of the Canadian Conference on Electrical & Computer Engineering (CCECE’99)1253–1258, Edmonton, 1999.
L. Han, J.F. Peters, S. Ramanna, R. Zhai Classifying faults in high voltage power systems: A rough-fuzzy neural computational approach. In [73], 47–54, 1999.
T. Kohonen. The self-organizing map.In:Proceedings IEEE, 78:1464–1480, 1990.
J. Komorowski, Z. Pawlak, L. Polkowski, A. Skowron. Rough sets: A tutorial. In[25]3–98, 1999.
G.W. Leibniz. In L. Couturat, editorOpuscles et Fragments Inedits de Leibniz256, Fèlix Alcan, Paris, 1903.
P.J. Lingras. Fuzzy-rough and rough-fuzzy serial combinations in neurocomputing.Neurocomputing36: 29–44, 2001.
P.J. Lingras. Rough neural networks. InProceedings of the 6th International Conference on Information Processing and Management of Uncertainty (IPMU’96)1445–1450, Universidad da Granada, Granada, 1996.
P.J. Lingras. Comparison of neofuzzy and rough neural networks.Information Sciences. An International Journal110: 207–215, 1998.
R. Milner.Communication and Concurrency.Prentice-Hall, Upper Saddle River, NJ, 1989.
R. Milner.Calculus of Communicating Systems. Report number ECS-LFCS-86–7 of Computer Science Department, University of Edinburgh, 1986.
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.
H.S. Nguyen, A. Skowron, M.S. Szczuka. Situation identification by unmanned aerial vehicle. In [74], 49–56, 2001.
H.S. Nguyen, M. Szczuka, D. Slgzak. Neural networks design: Rough set approach to real-valued data InProceedings of the 1st European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD’97)LNAI 1263, 359–366, Springer, Berlin, 1997.
T. Nguyen, R.W. Swiniarski, A. Skowron, J. Bazan, K. Thagarajan. Applications of rough sets, neural networks and maximum likelihood for texture classification based on singular decomposition. InProceedings of the 3rd International Workshop on Rough Sets and Soft Computing (RSSC’94)332–339, San Jose, CA, 1994.
S.K. Pal, S. Mitra. Multi-layer perceptron, fuzzy sets and classification.IEEE Transactions on Neural Networks3: 683–697,1992.
S.K. Pal, P. Mitra. Rough Fuzzy MLP: Modular evolution, rule generation and evaluation.IEEE Transactions on Knowledge and Data Engineering(in press).
S.K. Pal, A. Skowron, editors.Rough-Fuzzy Hybridization: A New Trend in Decision Making.Springer, Singapore, 1999.
Z. Pawlak.Rough Sets: Theoretical Aspects of Reasoning about Data.Kluwer, Dordrecht, 1991.
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, F. Gomide.An Introduction to Fuzzy Sets: Analysis and Design.MIT Press, Cambridge, MA, 1998.
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.
Z. Pawlak, J.F. Peters, A. Skowron, Z. Suraj, S. Ramanna, M. Borkowski. Rough measures and integrals: A brief introduction. In [72], 375–379, 2001.
W. Pedrycz, J.F. Peters. Learning in fuzzy Petri nets. In J. Cardoso, H. Scarpelli, editors.Fuzziness in Petri Nets858–886, Physica, Heidelberg, 1998.
J.F. Peters, A. Skowron, J. Stepaniuk. Rough granules in spatial reasoning. InProceedings of the Joint 9th International Fuzzy Systems Association (IFSA) World Congress and 20th North American Fuzzy Information Processing Society (NAFIPS) International Conference1355–1361, Vancouver, BC, 2001.
J.F. Peters, S. Ramanna. A rough set approach to assessing software quality: Concepts and rough Petri net model. In[25]349–380, 1999.
J.F. Peters, W. Pedrycz.Software Engineering: An Engineering Approach.Wiley, New York, 2000.
J.F. Peters, A. Skowron, Z. Suraj, L. Han, S. Ramanna. Design of rough neurons: Rough set foundation and Petri net model. InProceedings of the International Symposium on Methodologies for Intelligent Systems (ISMIS 2000)LNAI 1932, 283–291, Springer, Berlin, 2000.
J.F. Peters, A. Skowron, L. Han, S. Ramanna. Towards rough neural computing based on rough membership functions:Theory and application. In [74], 604–611,2001.
J.F. Peters, L. Han, S. Ramanna. Rough neural computing in signal analysis.Computationallntelligence1(3): 493–513, 2001.
L. Polkowski, A. Skowron.Approximate reasoning about complex objects in distributed systems: Rough mereological formalization. In W. Pedrycz, J.F. Peters, editorsComputational Intelligence in Software Engineering. Advances in Fuzzy Systems-Applications and Theory 16, 237–267, World Scientific, Singapore, 1998.
L. Polkowski, A. Skowron. Rough mereology: A new paradigm for approximate reasoning.International Journal Approximate Reasoning15(4): 333–365, 1996.
L. Polkowski, A. Skowron. Calculi of granules based on rough set theory: Approximate distributed synthesis and granular semantics for computing with words. In [73], 20–28, 1999.
L. Polkowski, A. Skowron. Rough-neuro computing. In[74]57–64, 2001.
L. Polkowski, A. Skowron. Towards adaptive calculus of granules. InProceedings of the 6th International Conference on Fuzzy Systems (FUZZ-IEEE’98)111–116, Anchorage AK, 1998.
A. Skowron, C. Rauszer. The discernibility matrices and functions in information systems. In R. Slowir¨ªski, editorIntelligent Decision Support: Handbook of Applications and Advances of the Rough Sets Theory331–362, Kluwer, Dordrecht, 1992.
A. Skowron. Toward intelligent systems: Calculi of information granules.Bulletin of the International Rough Set Society5(1/2):9–30,2001.
A. Skowron. Approximate reasoning by agents in distributed environments. In N. Zhong, J. Liu, S. Ohsuga, J. Bradshaw, editorsIntelligent Agent Technology: Research and Development. Proceedings of the 2nd Asia-Pacific Conference on IAT (APCIAT 2001)28–39, World Scientific, Singapore, 2001.
A. Skowron. Approximate reasoning by agents. InProceedings of the 2nd International Workshop of Central and Eastern Europe on Multi-Agent Systems (CEEMAS 2001)LNAI 2296, 3–14, Springer, Berlin, 2002.
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[73]357–365, 2001.
A. Skowron, J. Stepaniuk, S. Tsumoto. Towards discovery of information granules. InProceedings of the 3rd European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD’99), LNAI 1704, 542–547, Springer, Berlin, 1999.
A. Skowron, J. Stepaniuk. Tolerance approximation spaces.Fundamenta Informaticae27: 245–253, 1996.
A. Skowron, J. Stepaniuk. Information granules and approximation spaces. In Proceedings of the 7th International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems (IPMU’98), 1354–1361, Paris, 1998.
A. Skowron, J. Stepaniuk. Information granules: Towards foundations of granular computing.International Journal of Intelligent Systems16(1): 57–104, 2001.
A. Skowron, J. Stepaniuk. Information granule decomposition.Fundamenta Informaticae47(3/4): 337–350, 2001.
A. Skowron, J. Stepaniuk, J.F. Peters. Approximation of information granule sets. In[74]65–72, 2001.
A. Skowron, J. Stepaniuk, J.F. Peters. Hierarchy of information granules. In H.D. Burkhard, L. Czaja, H.S. Nguyen, P. Starke, editorsProceedings of the Workshop on Concurrency Specification and Programming (CSP 2001) 254–268, Warsaw, 2001.
A. Skowron, Z. Suraj. A parallel algorithm for real-time decision making: A rough set approach.Journal of Intelligent Information Systems7: 5–28, 1996.
R.W. Swiniarski.RoughNeuralLab software package. Developed at San Diego State University, San Diego, CA, 1995.
R. Swiniarski, F. Hunt, D. Chalvet, D. Pearson. Prediction system based on neural networks and rough sets in a highly automated production process. InProceedings of the 12th System Science ConferenceWroclaw, Poland, 1995.
R. Swiniarski, F. Hunt, D. Chalvet, D. Pearson. Intelligent data processing and dynamic process discovery using rough sets, statistical reasoning and neural networks in a highly automated production systems. InProceedings of the 1st European Conference on Application of Neural Networks in IndustryHelsinki, 1995.
R.W. Swiniarski. Rough sets and neural networks application to handwritten character recognition by complex Zernike moments. InProceedings of the 1st Internatonal Conference on Rough Sets and Current Trends in Computing (RSCTC’98)LNAI 1424, 617–624, Springer, Berlin, 1998.
R.W. Swiniarski, L. Hargis. Rough sets as a front end of neural networks texture classifiers.Neurocomputing: An International Journal36: 85–103, 2001.
M. S. Szczuka. Refining classifiers with neural networks.International Journal of Intelligent Systems16(1): 39–55, 2001.
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 Systems 449–470, Physica, Heidelberg, 1998.
M.S. Szczuka. Function approximation by neural networks with application of rough set methods. Master’s thesis, Faculty of Mathematics, Informatics and Mechanics, Warsaw University, 1995 (in Polish).
M.S. Szczuka. Symbolic methods and artificial neural networks in classifier construction, Ph.D. dissertation, Faculty of Mathematics, Informatics and Mechanics, Warsaw University, 2000 (in Polish).
M.S. Szczuka. Rough set methods for constructing artificial neural networks. In B.D. Czejdo, I.I. Est, B. Shirazi, B. Trousse, editorsProceedings of the 3rd Biennial Joint Conference on Engineering Systems Design and Analysis (ESDA’96)9–14, Montpellier, France, 1996.
A. Tarski. InIntroduction to Logic and to the Methodology of Deductive SciencesIV, 68–78. Oxford University Press, New York, 1965.
N. Wiener.Cybernetics or Control and Communication in the Animal and the Machine 2nd ed. MIT Press, Cambridge, MA, 1961.
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. A new direction in AI: Toward a computational theory of perceptions.AI Magazine22(1): 73–84, 2001.
T. Terano, T. Nishida, A. Namatame. S. Tsumoto, Y. Ohsawa, T. Washio, editors.New Frontiers in Artificial Intelligence. Joint JSAI 2001 Workshop Post ProceedingsLNAI 2253, Springer, Berlin, 2001.
N. Zhong, A. Skowron, S. Ohsuga, editors.New Directions in Rough Sets Data Mining and Granular-Soft ComputingLNAI 1711, Springer, Berlin, 1999.
W. Ziarko, Y.Y. Yao, editors.Proceedings of the 2nd International Conference on Rough Sets and Current Trends in Computing (RSCTC 2000)LNAI 2005, Springer, 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
Pal, S.K., Peters, J.F., Polkowski, L., Skowron, A. (2004). Rough-Neural Computing: An Introduction. 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_2
Download citation
DOI: https://doi.org/10.1007/978-3-642-18859-6_2
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-62328-8
Online ISBN: 978-3-642-18859-6
eBook Packages: Springer Book Archive