FuNN/2—a fuzzy neural network architecture for adaptive learning and knowledge acquisition

Please note that this is a searchable PDF derived via optical character recognition (OCR) from the original source document. As the OCR process is never 100% perfect, there may be some discrepancies between the document image and the underlying text.Fuzzy neural networks have several features that make them well suited to a wide range of knowledge engineering applications. These strengths include fast and accurate learning, good generalisation capabilities, excellent explanation facilities in the form of semantically meaningful fuzzy rules, and the ability to accommodate both data and existing expert knowledge about the problem under consideration. This paper investigates adaptive learning, rule extraction and insertion, and neural/fuzzy reasoning for a particular model of a fuzzy neural network called FuNN. As well as providing for representing a fuzzy system with an adaptable neural architecture, FuNN also incorporates a genetic algorithm in one of its adaptation modes. A version of FuNN—FuNN/2, which employs triangular membership functions and correspondingly modified learning and adaptation algorithms, is also presented in the paper.Unpublished[1] Yamakawa, T., Kusanagi, H., Uchino, E. and Miki, T., “A new Effective Algorithm for Neo Fuzzy Neuron Model”, in: Proceedings of Fifth IFSA World Congress, (1993) 1017-1020. [2] Hashiyama, T., Furuhashi, T., Uchikawa, Y., “A Decision Making Model Using a Fuzzy Neural Network”, in: Proceedings of the 2nd International Conference on Fuzzy Logic & Neural Networks, Iizuka, Japan, (1992) 1057-1060. [3] Kasabov, N., “Learning fuzzy rules and approximate reasoning in fuzzy neural networks and hybrid systems”, Fuzzy Sets and Systems, 82 (2), 1996, 135-149 [4] Kasabov, N., Foundations of Neural Networks, Fuzzy Systems and Knowledge Engineering, The MIT Press, CA, MA, 1996 [5] Kasabov, N., “Adaptable connectionist production systems”. Neurocomputing, 13 (2-4), 1996, 95-117 [6] Hauptmann, W., Heesche, K., A Neural Net Topology for Bidirectional Fuzzy-Neuro Transformation, in: Proceedings of the FUZZ-IEEE/IFES, Yokohama, Japan, (1995) 1511-1518. [7] Jang, R., ANFIS: adaptive network-based fuzzy inference system, IEEE Trans. on Syst.,Man, Cybernetics, 23(3), May-June 1993, 665-685 [8] Lin, C-T., Lin, C-J., Lee, C.T., Fuzzy adaptive learning control network with on-line learning, Fuzzy Sets and Systems, 71(1), 1995, 25-45 [9] Goldberg, D., Genetic Algorithms is Search, Optimization and Machine Learning, Addison Wesley, 1989 [10] Mang, G. Lan, H., Zhang, L. “A Genetic-based method of Generating Fuzzy Rules and Membership Functions by Learning from Examples”, in: Proceedings of International Conference on Neural Information Processing (ICONIP ’95) Volume One, 1995, 335-338 [11] Kasabov, N. Hybrid Connectionist Fuzzy Production Systems - Towards Building Comprehensive AI, Intelligent Automation and Soft Computing, 1:4 (1995) 351-360) [12] Carpenter, G., “Learning, Recognition, and Prediction by ART and ARTMAP Neural Networks”, in: Proceedings of ICNN’96, IEEE Press, Volume “Plenary Panel and Special Sessions, 1996, 244-249 [13] Kasabov, N., Investigating the adaptation and forgetting in fuzzy neural networks by using the method of training and zeroing”, in: Proceedings of the International Conference on Neural Networks ICNN’96, Plenary, Panel and and Special Sessions volume,1996, 118-123 [14] Kasabov, N., Advanced Neuro-Fuzzy Engineering for Building Intelligent Adaptive Information Systems, in: L.Reznick, V.Dimitrov, J.Kacprzyk (eds.) Fuzzy Systems Design: Social and Engineering Applications, Physica-Verlag (Springer Verlag), to appear in 199