Variations of the two-spiral task

Connection Science

Volumn 19, Issue 2, 2007, Pages 183-199

  Chalup, Stephan K ^a   Wiklendt, Lukasz ^a  

^a UNIVERSITY OF NEWCASTLE   (Australia)

Author keywords

Benchmarking; Classification; Generalisation; Neural networks; Support vector machines

Indexed keywords

BINARY CLASSIFICATION; GENERALISATION; PILOT STUDIES; RELATIVE ROTATION; SMALL VARIATIONS; VISUAL APPEALS;

BENCHMARKING; CLASSIFICATION (OF INFORMATION); SUPPORT VECTOR MACHINES;

NEURAL NETWORKS;

EID: 34250196183     PISSN: 09540091     EISSN: 13600494     Source Type: Journal    
DOI: 10.1080/09540090701398017     Document Type: Article

References (122)

1. D.W. Aha, Generalizing from case studies: A case study, in Proceedings of the Ninth International Conference on Machine Learning, D. Sleeman and P. Edwards, Eds, Morgan Kaufmann, San Mateo, CA, USA, 1992, pp. 1-10.
2. J.R. Alvarez-Sanchez, Injecting knowledge into the solution of the two-spiral problem, Neural Comput. and Appli. 8, 265-272, 1999.
3. M. Anthony and P.L. Bartlett, Neural Network Learning: Theoretical Foundations. Cambridge University Press, Cambridge, UK, 1999.
4. R.C. Archibald, The logarithmic spiral. American Mathematical Monthly 25, 189-193, 1918.
5. N.E. Ayat, M. Cheriet, L. Remaki and C.Y. Suen, KMOD-A new support vector machine kernel with moderate decreasing for pattern recognition. Application to digit image recognition, in Sixth International Conference on Document Analysis and Recognition (ICDAR'01). IEEE Computer Society, Los Alamitos, CA, USA, 2001, pp. 1215-1219.
6. A. Baraldi and E. Alpaydin, Constructive feedforward ART clustering networks - part II. IEEE Trans. Syst. Man Cybern. B, 13, 662-677, 2002.
7. P.L. Bartlett, The sample complexity of pattern classification with neural networks. The size of the weights is more important than the size of the network, IEEE Trans. Inf. Theory 44, 525-535, march 1998.
8. E.B. Baum and K.J. Lang, Constructing hidden units using examples and queries, in Advances in Neural Information Processing Systems (NIPS), P. Lippmann, J.E. Moody and S. Touretzky, Eds, Vol. 3, 1991, pp. 904-910.
9. R.E. Blahut, Digital Transmission of Information, MA: Addison-Wesley, Reading, 1990, pp. 306-313.
10. C.L. Blake and C.J. Merz, UCI repository of machine learning databases. Available on the internet at: http://www.ics.uci.edu/~mlearn/MLRepository.html (1998).
11. A.P. Bradley and B.C. Lovell, Inductive learning using multiscale classification, in A.C. Tsoi and T. Downs, Eds. The University of Queensland, Brisbane, Australia, Proceedings of the Fifth Australian Conference on Neural Networks, ACNN'94. 1994, pp. 133-136.
12. P.C. Bressloff and J.D. Cowan, Pattern formation, neural, in M.A. Arbib, (Ed), The Handbook of Brain Theory and Neural Networks (2nd edn), Cambridge, MA,US A: The MIT Press, 2003 pp. 859-863.
13. P.C. Bressloff, J.D. Cowan, M. Golubitsky, P.J. Thomas and M.C. Wiener, Geometric visual hallucinations, Euclidean symmetry and the functional architecture of striate cortex. Philos. Trans. Royal Soc. London B Biolo. Sci., 356, 299-330, March 2001.
14. J. Bruske and G. Sommer, Dynamic cell structure learns perfectly topology preserving map, Neural Comput. 7, 845-865, 1995.
15. G.A. Carpenter, S. Grossberg, N. Markuzon, J.H. Reynolds and D.B. Rosen, Fuzzy ARTMAP: a neural network architecture for incremental supervised learning of analog multidimensional maps. IEEE Trans. Neural Net. 3, 698-713, September 1992.
16. G.A. Carpenter, S. Grossberg and J.H. Reynolds, A fuzzy ARTMAP nonparametric probability estimator for non-stationary pattern recognition problems, IEEE Trans. Neural Netw, 6, 1330-1336, November 1995.
17. G. Casella and R.L. Berger, Statistical Inference (2nd edn). Duxbury Press, Pacific Grove, California, 2002.
18. J.L. Castro, M. Delgado and C.J. Mantas, SEPARATE: a machine learning method based on semi-global partitions, IEEE Trans. Neural Netw., 11, 710-720, May 2000.
19. N. Chaiyaratana and A.M.S.Zalzala, Evolving hybrid RBF-MLP networks using combined genetic/unsupervised/supervised learning, in UKACC International Conference on Control '98, 1-4 September 1998, University of Wales, Swansea, UK, IEE Conference Publications No. 455. Institution of Electrical Engineers, London, UK, 1998, pp. 330-335.
20. J. L. Chen and J. Y. Chang, Fuzzy perceptron neural networks for classifiers with numerical data and linguistic rules as inputs, IEEE Trans. Fuzzy Syst., 8, 730-745, December 2000.
21. K. Chen and D. Wang, Perceiving geometric patterns: From spirals to inside-outside relations, IEEE Trans. Neural Netw., 12, 1084-1102, September 2001.
22. K. Chen, L. Yang, Y. Xiang and H. Chi. A self-generating modular neural network architecture for supervised learning. Neurocomputing, 16, 33-48, 1997.
23. G. Cheng, T. Liu, J. Han and Z. Wang, A. Towards growing self-organizing neural networks with fixed dimensionality. Trans. Eng. Comp. Technol., 15, 268-272, October 2006.
24. G. Cheng, Z. Song, J. Yang and R. Gao, B. On growing self-organizing neural networks without fixed dimensionality, in International Conference on Computational Intelligence for Modelling, Control and Automation, 2006 and International Conference on Intelligent Agents, Web Technologies and Internet Commerce. (CIMCA-IAWTIC'06), IEEE Comp. Soc., November 2006, pp. 164-168.
25. G. Cheng and A. Zell, Externally growing cell structures for pattern classification, in Proceedings of the Second ICSC Symposium on Neural Computation - NC'2000, H. Bothe and R. Rojas, Eds, ICSC Academic Press, Canada/Switzerland, 2000, pp. 233-239.
26. C.-C. Chiang and H.-C. Fu, 1994. A divide-and-conquer methodology for modular neural network design, in IEEE International Conference on Neural Networks 1994 (ICNN'94). IEEE World Congress on Computational Intelligence, Vol. 1, 1994. pp. 119-124.
27. J.-H. Chiang and P.-Y. Hao, Support vector learning mechanism for fuzzy rule-based modeling: A new approach, IEEE Trans. Fuzzy Syst. 12, 1-12, February 2004.
28. H. Chua, J. Jia, L. Chen and Y. Gong, Solving the two-spiral problem through input data encoding. Electroni. Lett., 31, 813-814, 1995.
29. I.B. Ciocoiu, A modular feedforward network for solving classification problems, in Proceedings of NATO Advanced Research Workshop on: Limitations and Future Trends in Neural Computation, LFTNC- '01, Siena, Italy, 22-24 October, 2001, M. Maggini (Ed.), pp. 69-72.
30. I.B. Ciocoiu, Hybrid feedforward neural networks for solving classification problems, Neural Process, Lett., 16, 81-91, 2002a.
31. I.B. Ciocoiu, RBF networks training using a dual extended Kalman filter, Neurocomputing, 48, 609-622, 2002b.
32. F.J. de Souza, M.M.R. Vellasco and M.A.C. Pacheco, Hierarchical neuro-fuzzy quadtree models. Fuzzy Sets Syst., 130, 189-205, September 2002.
33. J. Denker D. Schwartz, B. Winner S. Solla, R. Howard, L. Jackel and J.J. Hopfield, Large automatic learning, rule extraction, and generalization, Complex Syst., 1, 877-922, 1987.
34. T. Denoeux and R. Lengelle, Initializing backpropagation networks with prototypes, Neural Netw., 6, 351-363, 1993.
35. B. Dolin, M.G. Arenas, J.J. Merelo, Opposites attract: Complementary phenotype selection for crossover in genetic programming, in J.-J.M. Guervós, P. Adamidis, H.-G. Beyer, J.-L. Fernélndez-Villacanas and H.-P. Schwefel, Eds., Parallel problem solving from nature - PPSN VII, in 7th International Conference, Granada, Spain, 7-11, September, 2002. Proceedings. Vol. 2439 of Lecture Notes in Computer Science (LNCS). Springer-Verlag, pp. 142-152.
36. H. Du and Y.Q. Chen, 2007. Rectified nearest feature line segment for pattern classification, Pattern Recognit. 40, 1486-1497.
37. S.E. Fahlman, An empirical study of learning speed in back-propagation networks. Computer Science Department Technical Report CMU-CS-88-162, Carnegie Mellon University, Pittsburgh PA, 1998a.
38. S.E. Fahlman, Faster-learning variations on back-propagation: an empirical study, in Proceedings 1988 Connectionist Models Summer School, D.S. Touretzky, G.E. Hinton and T.J. Sejnowski, Eds, Morgan Kaufmann Publishers, Inc. San Mateo, CA: pp. 38-51. 1998b.
39. S.E. Fahlman and C. Lebiere, The cascade-correlation learning architecture, in Advances in Neural Information Processing Systems (NIPS) D.S. Touretzky (Ed.), Vol. 2, 1990, pp. 524-532.
40. S.E. Fahlman and C. Lebiere, The cascade-correlation learning architecture. Technical Report CMU-CS-90-100, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, August 1991.
41. G. Fahner and R. Eckmiller, Structural adpation of parsimonious higher-order neural classifiers. Neural Netw., 7, 279-289, 1994.
42. W. Fan and L. Zhang, Applying SP-MLP to complex classifcation problems. Pattern Recognit. Lett., 21, 9-19, 2000.
43. B. Fritzke, Growing cell structures a self-organizing network for unsupervised and supervised learning, Neural Netw, 7, 1441-1460, 1994.
44. H.-C. Fu, Y.-P. Lee, C.-C. Chiang and H.-T. Pao, Divide-and-conquer learning and modular perceptron networks, IEEE Trans. Neural Netw., 12, 250-263, March 2001.
45. I. Galleske and J. Castellanos, Optimization of the kernel functions in a probabilistic neural network analyzing the local pattern distribution, Neural Compu., 14, 1183-1194, 2002.
46. M.S. Glassman, A network of localized linear discriminants, in Advances in Neural Information Processing Systems (NIPS) J.E. Moody, S.J. Hanson and R. Lippmann, Eds, Vol. 4 Morgan Kaufmann, pp. 1102-1109, 1992.
47. S. Grossberg and L. Wyse, A neural network architecture for figure-ground separation of connected scenic figures, Neural Netw., 4, 723-742, 1991.
48. J. Han and C. Moraga, Hybrid nets with Variable parameters: a novel approach to fast learning under backpropagation, in INBS '95: Proceedings of the First International Symposium on Intelligence in Neural and Biological Systems, IEEE Computer Society, Washington, DC, USA, 1995, pp. 72-75.
49. P. Hilton, D. Holton and J. Pedersen, Mathematical Reflections in a Room with many Mirrors. Springer-Verlag, New York, 1997.
50. M.J.J. Holt, Sequential learning of casasent network classifiers: constructing piecewise spherical decision boundaries, in Proceedings of the International Conference of Artificial Neural Networks (ICANN'94), Sorrent M. Marinaro and P.G. Morasso, Eds, Springer-Verlag, Heidelberg, 1994a, pp. 1412-1415.
51. M.J.J. Holt, A weight learning strategy for sequential construction of casasent network classifiers, in Proceedings of the International Conference of Artificial Neural Networks (ICANN'94), Sorrent. M. Marinaro and P.G. Morasso, Eds, Springer-Verlag, Heidelberg, 1994b, pp. 1416-1419.
52. I. Howard, Proposals for the study of anomalous perceptual schemata. Perception. 3, 497-513, 1974.
53. D.-S. Huang and W.-B. Zhao, Determining the centers of radial basis probabilistic neural networks by recursive orthogonal least square algorithms, Appl. Math. Comput., 162, 461-473, March 2005.
54. J.-N. Hwang, S.-S. You, S.-R. Lay and I.-C. Jou, The cascade-correlation learning: a projection pursuit learning perspective, IEEE Trans. Neural Netw., 7, 278-289, March 1996.
55. J. Jia and H. Chua, Solving the two-spiral problem through input data representation, in Proceedings of the IEEE International Conference on Neural Networks, Vol. 1. 1995, pp. 132-135.
56. H. Juille and J.B. Pollack, Co-evolving intertwined spirals, in Evolutionary Programming V: Proceedings of the Fifth Annual Conference on Evolutionary Programming, L.J. Fogel, P.J. Angeline and T. Baeck, Eds, The MIT Press, Cambridge, MA, USA, 1996, pp. 461-467.
57. S.V. Kamarthi and S. Pittner, Accelerating neural network training using weight extrapolations, Neural Netw., 12, 1285-1299, 1999.
58. W. Kaminski and P. S trumillo, Kernel orthonormalization in radial basis function neural networks, IEEE Trans. Neural Netw., 8, 1177-1183, September 1997.
59. N.B. Karayiannis, Hybrid learning schemes for fast training of feed-forward neural networks, Math. Comp. Simul., 41, 13-28, 1996.
60. J. Keuchel, C. Schnörr, C. Schellewald and D. Cremers, Binary partitioning, perceptual grouping, and restoration with semidefinite programming. IEEE Trans. Pattern Analy. Mach. Intelli., 25, 1364-1379, November 2003.
61. J.R. Koza, Genetic Programming: On the Programming of Computers by Means of Natural Selection. MA, USA: The MIT Press, Cambridge, 1992.
62. L.I. Kuncheva, Initializing of an RBF network by a genetic algorithm, Neurocomputing, 14, 273-288, 1997.
63. J.J.T. Lahnajärvi, M.I. Lehtokangas and J.P.P. Saarinen, Evaluation of constructive neural networks with cascaded architectures, Neurocomputing, 48, 573-607, October 2002.
64. K.J. Lang and M.J. Witbrock, Learning to tell two spirals apart, in Proceedings 1988 Connectionist Models Summer School, Morgan Kaufmann, Los Altos, CA: D. Touretzky, G. Hinton and T. Sejnowski, Eds, 1988, pp. 52-59.
65. E.W.M. Lee, C.P. Lim, R.K.K. Yuen and S.M. Lo, A hybrid neural network model for noisy data regression. IEEE Trans. Syst. Man Cyb. B: Cyb., 34, 951-960, April 2004.
66. Y.-P. Lee and H.-C. Fu, Weight estimation for the learning of modular perceptron networks, in Neural Networks for-Signal Processing IX, Proceedings of the 1999 IEEE Signal Processing Society Workshop, 1999, pp. 103-111.
67. M. Lehtokangas, Determining the number of centroids for CMLP network, Neural Netw., 13, 525-531, 2000.
68. M. Lehtokangas and J. Saarinen, Centroid based multilayer perceptron networks, Neural Process. Lett. 7, 101-106, April 1998a.
69. M. Lehtokangas and J. Saarinen, Weight initialization with reference patterns, Neurocomputing, 20, 265-278, August 1998b.
70. B.C. Lovell and A.P. Bradley, The multiscale classifier, IEEE Trans. Patt. Anal. Mach. Intell., 18, 124-137, February 1996.
71. B.-L. Lu and M. Ito, Task decomposition and module combination based on class relations: A modular neural network for pattern classification, IEEE Trans. Neural Netw., 10, 1244-1256, September 1999.
72. W.S. McCulloch and W. Pitts, A logical calculus of ideas immanent in nervous activity, Bull. Math. Biophys., 5, 115-133, 1943.
73. M.L. Minsky and S. Papert, Perceptions: an introduction to Computational Geometry, Cambridge, MA, USA: The MIT Press, 1969.
74. M.L. Minsky and S. Papert, Perceptions: an introduction to Computational Geometry, (expanded edition), Cambridge, MA, USA: The MIT Press, 1988.
75. E. Mizutani and S.E. Dreyfus, MLP's hidden node saturations and insensitivity to initial weights in two classification benchmark problems: parity and two-spirals, in Proceedings of the 2002 International Joint Conference on Neural Networks (IJCNN '02), Vol. 3, IEEE Press, 2002, pp. 2831-2836.
76. S. Osowski, P. Bojarczak and M. Stodolski, Fast second order learning algorithm for feedforward multilayer neural networks and its applications, Neural Netw., 9, 1583-1596, 1996.
77. G. Patanè and M. Russo, Fully automatic clustering system, IEEE Trans. Neural Netw., 13, 1285-1298, November 2002.
78. K. Pelckmans, J.A.K. Suykens, T. Van Gestel, J. De Brabanter, L. Lukas, B. Hamers, B. De Moor and J. Vandewalle, LS-SVM lab: a Matlab/C toolbox for least squares support vector machines. Internal Report 02-44, ESAT-SISTA, K.U. Leuven, Belgium, Leuven, Belgium, 2002.
79. M.A. Potter and K.A. De Jong, Cooperative coevolution: an architecture for evolving coadapted subcomponents, Evol. Comp., 8, 1-29, 2000.
80. L. Prechelt, 1994. PROBEN 1 - a set of benchmarks and benchmarking rules for neural network training algorithms. Technical report 21, Universität Karlsruhe; Institut für Programmstrukturen und Datenorganisation, Germany.
81. J.R. Quinlan, C4.5: Programs for Machine Learning, San Francisco, CA, USA: Morgan Kaufmann Publishers Inc., 1993.
82. B. Ribeiro, On data based learning using support vector clustering, in Proceedings of the 9th International Conference on Neural Information Processing (ICONIP '02), L. Wang, J.C. Rajapakse, K. Fukushima, S.-Y. Lee and X. Yao, Eds, Vol. 5, 2002, pp. 2516-2521.
83. S. Ridella, S. Rovetta and R. Zunino, Circular backpropagation networks for classification. IEEE Trans. Neural Netw., 8, 84-97, January 1997.
84. S. Ridella, S. Rovetta and R. Zunino, Representation and generalization properties of class-entropy networks. IEEE Trans. Neural Netw., 10, 31-47, January 1999.
85. F. Rosenblatt, The perceptron: a probabilistic model for information storage and organization in the brain, Psychol. Rev. 65, 386-408, 1958.
86. R. Setiono, A neural network construction algorithm which maximizes the likelihood function, Connection Sci., 7, 147-166, 1995.
87. Y. Shang and B.W. Wah, Global optimization for neural network training. IEEE Comp., 29, 45-54, 1996.
88. T.R. Shultz and J.L. Elman, Analysing cross connected networks, in Advances in Neural Information Processing Systems (NIPS), Vol. 6, 1994, pp. 1117-1124.
89. T.R. Shultz, Y. Oshima-Takane and Y. Takane, Analysis of unstandardized contributions in cross connected networks, in Advances in Neural Information Processing Systems (NIPS), Vol. 7, 1995 pp. 601-608.
90. S. Singh, 2D spiral pattern recognition with probabilistic measures, Patt. Recog. Lett., 19, 141-147, 1998.
91. S. Singh, Neural learning of spiral structures, in Proceedings International Conference on Advances in Pattern Recognition (ICAPR'98), Singh, S. (Ed.). Plymouth UK, Springer-Verlag, 1998b, pp. 226-231.
92. S. Singh, Quantifying structural time varying changes in helical data, Neural Comp. Appli., 10, 148-154, 2001.
93. F. Smieja, The pandemonium systems of reflective agents, IEEE Trans. Neural Netw., 7, 97-106, January 1996.
94. M. Solazzi and A. Uncini, Artificial neural networks with adaptive multidimensional spline activation functions, in IJCNN-2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, S.-I. Amari, C.L. Giles, M. Gori and V. Piuri, Eds, Como, Italy, 24-27 July, 2000, Vol. 3, IEEE Computer Society, pp. 471-476.
95. J.M. Sopena, E. Romero and R. Alquzar, Neural networks with periodic and monotonic activation functions: a comparative study in classification problems, in Proceedings of the 9th International Conference on Artificial Neural Networks (ICANN'99), D. Willshaw and A. Murray, Eds, University of Edinburgh. IEE Conference Publication No. 470, 1999, pp. 323-328.
96. L. Su and S.-U. Guan, Two-dimensional extensions of cascade correlation networks, in The Fourth International Conference on High-Performance Computing in the Asia-Pacific Region (HPC-ASIA 2000), Vol. 1, IEEE Computer Society, 2000, pp. 138-141.
97. C.T. Sun and J.S. Jang, A neuro-fuzzy classsifier and its applications, in Proceedings of the Second IEEE International Conference on Fuzzy Systems, San Francisco, CA, USA, March 1993, Vol. 1, 1993, pp. 94-98.
98. J.A.K. Suykens, T. Van Gestel, J. De Brabanter, B. De Moor and J. Vandewalle, Least Squares Support Vector Machines, Singapore: World Scientific Pub. Co., and 2002.
99. J.A.K. Suykens and J. Vandewalle, Least squares support vector machine classifiers, Neural Process. Lett., 9, 293-300, 1999a.
100. J.A.K. Suykens and J. Vandewalle, Training multilayer perceptron classifiers based on a modified support vector method. IEEE Trans. Neural Netw., 10, 907-911, July 1999b.
101. C.-C. Teng and B.W. Wan, Automated learning for reducing the configuration of a feed-forward neural network, IEEE Trans. Neural Netw., 1, 1072-1085, September 1996.
102. P. Thangavel and T. Kathirvalavakumar, Simultaneous perturbation for single hidden layer networks-cascade learning, Neurocomp., 50, 193-209, January 2003.
103. W. Ting and Y. Sugai, A wavelet neural network for January 2003. the approximation of nonlinear multi-variable function, in 1999 IEEE International Conference on Systems, Man, and Cybernetics, IEEE SMC '99 Conference Proceedings, October 1999. Vol. 3, pp. 378-383.
104. D. Tomandl and A. Schober, A modified general regression neural network (MGRNN) with new, efficient training algorithms as a robust 'black box'-tool for data analysis, Neural Netw., 14, 1023-1034, 2001.
105. N.K. Treadgold and T.D. Gedeon, A cascade network algorithm employing progressive RPROP. in Biological and Artificial Computation: from Neuroscience to Technology, International Work-Conference on Artificial and Natural Neural Networks, IWANN '97, Lanzarote, Canary Islands, Spain, 4-6, June, J. Mira, R. Moreno-Díaz and J. Cabestany, Eds, 1997, Proceedings, Vol. 1240 of Lecture Notes in Computer Science (LNCS). Springer-Verlag, pp. 733-742.
106. N.K. Treadgold and T.D. Gedeon, Extending and benchmarking the CasPer algorithm, in Advanced Topics in Artificial Intelligence, 10th Australian Joint Conference on Artificial Intelligence, AI'97, Perth, Australia, A. Satter, (Ed.), Vol. 1342 of Lecture Notes in Computer Science (LNCS). Springer-Verlag, 1997b, pp. 398-406.
107. N.K. Treadgold and T.D. Gedeon, Exploring constructive cascade networks, IEEE Trans. Neural Netw., 10, 1335-1350, November 1999.
108. L.G. Valiant, A theory of the learnable. Comm. ACM, 27, 1134-1142, November 1994.
109. V.N. Vapnik, Estimation of Dependences Based on Empirical Data [in Russian]. Nauka, Moscow, English translation: New York: Springer-Verlag, 1979.
110. V.N. Vapnik, The Nature of Statistical Learning Theory. New York, NY, USA: Springer-Verlag, 1995.
111. B.W. Wah and M. Qian, Constrained formulations for neural network training and their applications to solve the two-spiral problem, In Proceedings of the 5th International Conference on Computer Science, and Informatics and 5th Joint Conference on Information Sciences, Vol. 5, 2000, pp. 598-601.
112. M.K. Weir and L.H. Chen, Neural training and generalisation of sequences using continuous temporal structure, in 1991 IEEE International Joint Conference on Neural Networks, Vol. 3. IEEE, 1991 pp. 2027-2032.
113. E.W. Weisstein, Eric Weisstein's world of mathematics-a Wolfram web resource. Available online at: http://mathworld.wolfram.com (2003).
114. M. White, T. Sejnowski, C. Rosenberg, N. Qian, R.P. Gorman, A. Wieland, D. Deterding, M. Niranjan and T. Robinson, Bench: CMU neural networks benchmark collection. Available at: http://www-2.cs.cmu.edu/afs/cs/project/airepository/ ai/areas/neural/bench/cmu/0.html (1995).
115. D. Whitley and N. Karunanithi, Generalization in feed-forward neural networks, in Proceedings of the International Joint Conference on Neural Networks (IJCNN'91). Vol. II, IEEE Press, 1991, pp. 77-82.
116. J.R. Williamson, Gaussian ARTMAP: a neural network for fast incremental learning of noisy multidimensional maps. Neural Netw. 9, 881-897, 1996.
117. Q. Xiong, K. Hirasawa, J. Hu and J. Murata, Comparative study between functions distributed network and ordinary neural network, in IEEE International Conference on Systems, Man, and Cybernetics, Vol. 3, 2001 pp. 1548-1553.
118. Q. Xiong, K. Hirasawa, J. Hu and J. Murata, A functions localized neural network with branch gates, Neural Netw., 16, 1461-1481, 2003.
119. J.-M. Yang and C.-Y. Kao, A robust evolutionary algorithm for training neural networks, Neural Compt. Appli., 10, 214-230, 2001.
120. S. Young and T. Downs, CARVE-a constructive algorithm for real-valued examples. IEEE Trans. Neural Netw., 9, 1180-1190, November 1998.
121. C.-C. Yu and Y.-C. Tang, B.-D, Liu, An adaptive activation function for multilayer feedforward neural network, in TENCON'02. Proceedings. 2002 IEEE Region 10 Conference on Computers, Communications, Control and Power Engineering, Vol. 1, 2002 pp. 645-650.
122. L. Zhang and B. Zhang, A geometrical representation of McCulloch-Pitts neural model and its applications, IEEE Trans. Neural Netw., 10, 925-929, July 1999.