Actas de congresos
Neurons And Neural Fuzzy Networks Based On Nullnorms
Registro en:
9780769533612
Proceedings - 10th Brazilian Symposium On Neural Networks, Sbrn 2008. , v. , n. , p. 123 - 128, 2008.
10.1109/SBRN.2008.15
2-s2.0-58049204099
Autor
Hell M.
Gomide F.
Costa Jr. P.
Institución
Resumen
This paper suggests a new type of elementary unit for neural fuzzy networks based on the concept of nullnorm. A nullnorm is a category of fuzzy set-oriented operators that generalizes triangular norms and conorms. The new unit, called nullneuron, is a generalization of and/or logic-based neurons parametrized by an element u, called the absorbing element. If the absorbing element u = 0, then the nullneuron becomes an and neuron and if u = 1, then the nullneuron becomes a dual or neuron. The paper also addresses two learning schemes for a class of hybrid neural fuzzy networks with nullneurons. The first scheme uses the gradient descent technique and the second reinforcement learning. Both learning schemes adjust not only the weights associated with the inputs of the nullneurons, but also the role of the nullneuron in the network (and or or) by individually adjusting the parameter u of each nullneuron. The neurofuzzy network presented here is more general than alternative approaches discussed in the literature because they allow different triangular norms in the same network structure. Experimental results show that nullneuron-based networks provide accurate results with low computational effort. © 2008 IEEE.
123 128 Box, G.E.P., Jenkins, G.M., (1976) Time Series Analysis- Forecasting and Control, , Holden Day, CA, USA, second edition Delgado, M., Gmez-Skarmeta, A.F., Martin, F., Fuzzy clustering based rapid prototyping for fuzzy rule-based modeling (1997) IEEE Trans. on Fuzzy Systems, 5, pp. 223-233. , May Figueiredo, M., Ballini, R., Soares, S., Andrade, M., Gomide, F., Learning algorithms for a class of neurofuzzy network and application (2004) IEEE Trans. on System, Man and Cybernetics - Part C, 34 (3), pp. 293-301 Gomide, F., Pedrycz, W., (2007) Fuzzy Systems Engineering: Toward Human-Centric Computing, , Wiley Interscience, NJ, USA M. Hell, P. Costa-Jr., and F. Gomide. Nullneurons-based hybrid neurofuzzy network. In Proceedings of Annual Meeting of the North American Fuzzy Information Processing Society, NAFIPS 07, pages 331-336, San Diego-CA, USA, June 2007Hell, M., Costa-Jr, P., Gomide, F., Hybrid neurofuzzy computing with nullneurons (2008) Proceedings of IEEE World Congress on Computational Intelligence - WCCI 2008, , Hong Kong, China, June Jang, R., Anfis: Adaptive network based fuzzy inference system (1993) IEEE Trans. on Systems Man and Cybernetics, 23 (3), pp. 665-685 Lin, C.T., Lee, C.S., (1996) Neural Fuzzy Systems, , Prentice-Hall, NJ, USA Pedrycz, W., A identification algorithm in fuzzy relational systems (1984) Fuzzy Sets and Systems, 13, pp. 153-167 Pedrycz, W., Neurocomputations in relational systems (1991) IEEE Trans. on Pattern Analysis and Machinne Intelig, 13 (3). , 289-297 Pedrycz, W., Logic-based neurocomputing with unineurons (2006) IEEE Trans. on Fuzzy Systems, 14 (6), pp. 860-873 Rutkowski, L., Cpalka, K., Design and learning of adjustable quasi-triangular norms with applications to neurofuzzy systems (2005) IEEE Trans. on Neural Networks, 13 (1), pp. 140-151 Calvo, B.D.B.T., Fodor, J., The functional equations of frank ans alsina for uninorms and nullnorms (2001) Fuzzy Sets and Systems, 120, pp. 385-394 Caminhas, F.G.W., Tavares, H., Pedrycz, W., Fuzzy set based neural networks: Structure, learning and application (1999) Journal of Advanced Computational Intelligence, 3 (3), pp. 151-157 Xu, W., Lu, Y.Z., Fuzzy model identification and selflearning for dynamic systems (1987) IEEE Trans. on System, Man and Cybernetics, SMC-17, pp. 683-689. , July Yager, R., Rybalov, A., Uninorm aggregation operators (1996) Fuzzy Sets and Systems, 80 (1), pp. 111-120 Yoshinari, Y., Pedrycz, W., Hirota, K., Construction of fuzzy models through clustering techniques (1993) Fuzzy Sets and Systems, 54, pp. 157-165