PSECMAC: A novel self-organizing multiresolution associative memory architecture

IEEE Transactions on Neural Networks

Volumn 19, Issue 4, 2008, Pages 689-712

  Teddy, S D ^a,b   Quek, C ^a   Lai, E M K ^c  

^a NANYANG TECHNOLOGICAL UNIVERSITY   (Singapore)

^b INSTITUTE FOR INFOCOMM RESEARCH   (Singapore)

^c MASSEY UNIVERSITY   (New Zealand)

Author keywords

Associative memory; Brain inspired; Cerebellar model articulation controller (CMAC); Cerebellum; Learning convergence; Multiresolution; Neural networks; Pseudo self evolving CMAC (PSECMAC)

Indexed keywords

BRAIN; COMPUTATIONAL METHODS; COMPUTER SIMULATION; MATHEMATICAL MODELS; NEUROPHYSIOLOGY; OPTIMIZATION; PATTERN RECOGNITION;

CEREBELLAR MODEL ARTICULATION CONTROLLER (CMAC); NEUROPHYSIOLOGICAL PROPERTIES;

NEURAL NETWORKS;

ARTICLE; ARTIFICIAL NEURAL NETWORK; BIOLOGICAL MODEL; CEREBELLUM; COMPUTER SIMULATION; CYTOLOGY; HUMAN; LEARNING; MEMORY; NERVE CELL NETWORK; NERVE CELL PLASTICITY; PHYSIOLOGY; SYNAPSE;

ASSOCIATION LEARNING; CEREBELLUM; COMPUTER SIMULATION; HUMANS; MEMORY; MODELS, NEUROLOGICAL; NERVE NET; NEURAL NETWORKS (COMPUTER); NEURONAL PLASTICITY; SYNAPSES;

EID: 42549143443     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/TNN.2007.912300     Document Type: Article

References (109)

1. F. A. Middleton and P. L. Strick, "The cerebellum: An overview," Trends Cogn. Sci., vol. 27, no. 9, pp. 305-306, 1998.
2. J. S. Albus, "Marr and Albus theories of the cerebellum: Two early models of associative, memory," Proc. 34th IEEE Comput. Sci. Int. Conf.: Intell. Leverage, pp. 577-582, 1989.
3. H. Eichenbaum, The Cognitive Neuroscience of Memory: An Introduction Oxford, U.K.: Oxford Univ. Press, 2002.
4. J. S. Albus, "A new approach to manipulator control: The cerebellar model articulation controller (CMAC)," Trans. ASME, Ser. G, J. Dyn. Syst. Meas. Control, vol. 97, pp. 220-227, 1975.
5. J. S. Albus, "Data storage in cerebellar model articulation controller (CMAC)," Trans. ASME, Ser. G, J. Dyn. Syst. Meas. Control vol. 97, pp. 228-233, 1975.
6. F. H. Glanz, W. T. Miller, and L. G. Kraft, "An overview of the CMAC neural network," in Proc. IEEE Conf. Neural Netw. Ocean Eng., Washington, D.C., 1991, pp. 301-308.
7. W. T. Miller, F. H. Glanz, and L. G. Kraft, "CMAC: An associative neural network alternative to backpropagation," Proc. IEEE, vol. 78, no. 10, pp. 1561-1567, Oct. 1990, Special issue on Neural Networks.
8. T. Yamamoto and M. Kaneda, "Intelligent controller using CMACs with self-organized structure and its application for a process system," IEICE Trans. Fundam., vol. E82-A, no. 5, pp. 856-860, 1999.
9. S. Ku, G. A. Larsen, and S. Cetinkunt, "Fast servo control for ultraprecision machining at extremely low feed rates," Mechatronics pp. 381-393, 1998.
10. G. A. Larsen, S. Cetinkunt, and A. Donmez, "CMAC neural network control for high precision motion control in the presence of large friction," J. Dynamic Syst. Meas. Control, vol. 117, DD. 415-420, 1995.
11. S. Cetinkunt and A. Donmez, "CMAC learning controller for servo control of high precision machine tools," in Proc. Amer. Control Conf., San Francisco, CA, 1993, pp. 1976-1980.
12. L. G. Kraft, W. T. Miller, and D. Dietz, "Development and application of CMAC neural network-based control," in Handbook of Intelligent Control: Neural, Fuzzy, and Adaptive Approaches, D. A. White and D. A. Sofge, Eds. New York: Van Nostrand, 1992, pp. 215-232.
13. C. S, Lin and K. Hyougsuk, "CMAC-based adaptive critic self-learning control," IEEE Trans. Neural Netw., vol. 2, no. 5, pp. 530-533, Sep. 1991.
14. S. Commuri, S. Jagannathan, and F. L. Lewis, "CMAC neural network control of robot manipulators," J. Robot. Syst., vol. 14, no. 6, pp. 465-482, 1997.
15. H. Kano and K. Takayama, "Learning control of robotic manipulators based on neurological model CMAC," in Proc. 11th Triennial World Congr. Int. Fed. Autom. Control, Tallinn, Russia, 1990, pp. 249-254.
16. W. T. Miller, F. H. Glanz, and L. G. Kraft, "Application of a general learning algorithm to the control of robotic manipulators," Int. J. Robot. Res., vol. 6, no. 2, pp. 84-98, 1987.
17. A. Wahab, E. C. Tan, and H. Abut, "HCMAC amplitude spectral subtraction for noise cancellation," in Proc. Int. Conf. Neural Inf. Process. 2001 [Online]. Available: Http://www.cse.cuhk.edu.hk/~appna/ proceedings/iconip2001
18. K. L. Huang, S. C. Hsieh, and H. C. Fu, "Cascade-CMAC neural network applications on the color scanner to printer calibration," in Proc. Int. Conf. Neural Netw., 1997, vol. 1, pp. 10-15.
19. J. Ker, C. Hsu, Y. Kuo, and B. Liu, "A fuzzy CMAC model for color reproduction," Fuzzy Sets Syst., vol. 91, no. 1, pp. 53-68, 1997.
20. C. He. L. Xu. and Y. Zhang, "Learning convergence of CMAC algorithm," Neural Process. Lett., vol. 14, no. 1, pp. 61-74, 2001.
21. C. S. Lin and C. T. Chiang, "Learning convergence of CMAC technique," IEEE Trans. Neural Netw., vol. 8, no. 6, pp. 1281-1292, Nov. 1997.
22. Y. Wong and A. Sideris, "Learning convergence in the cerebellar model articulation controller," IEEE Trans. Neural Netw., vol. 3, no. 1, pp. 115-121, Jan. 1992.
23. H. M. Lee, C. M. Chen, and Y. F. Lu, "A self-organizing HCMAC neural network classifier," IEEE Trans. Neural Netw., vol. 14, no. 1, pp. 15-27, Jan. 2003.
24. M. F. Yeh and H. C. Lu, "On-line adaptive quantization input space in CMAC neural network," in Proc. IEEE Int. Conf. Syst. Man Cybern., 2002, vol. 4.
25. H. Kim and C. S. Lin, "Use of adaptive resolution for better CMAC learning," in Proc. Int. Joint Conf. Neural Netw., 1992, vol. 117, pp. 517-522.
26. X. Gao, C. Wang, X. M. Gao, and S. J. Ovaska, "A new CMAC neural network model with adaptive quantization input layer," in Proc. 3rd. Int. Conf. Signal Process., 1996, vol. 2, pp. 1417-1420.
27. J. Moody, "Past-learning in multi-resolution hierarchies," in Advanced Neural Information Processing Systems. San Mateo, CA: Morgan Kaufmann, 1989, vol. 14, pp. 29-38.
28. A. Menozzi and M. Chow, "On the training of a multi-resolution CMAC neural network," in Proc. 23rd Int. Conf. Ind. Electron. Control Instrum., 1997, vol. 3, pp. 1130-1135.
29. J. Ozawa, I. Hayashi, and N. Wakami, "Formulation of CMAC-fuzzy system," in Proc. IEEE Int. Conf. Fuzzy Syst., 1992, pp. 1179-1186.
30. J. H. Nie and D. A. Linkens, "A fuzzified CMAC self-learning controller," in Proc. 2nd IEEE Int. Conf. Fuzzy Syst., 1993, vol. 1, pp. 500-505.
31. K. Zhang and F. Qian, "Fuzzy CMAC and its application," Proc. 3rd World Congr. Intell. Control Autom., pp. 944-947, 2000.
32. C. C. Jou, "A fuzzy cerebellar model articulation controller," in Proc. IEEE Int. Conf. Fuzzy Syst., 1992, pp. 1171-1178.
33. D. Kim, "A design of CMAC-based fuzzy logic controller with fast learning and accurate approximation," Fuzzy Sets Syst., vol. 125, no. 1, pp. 93-104, 2002.
34. S. H. Lane, D. A. Handelman, and J. J. Getfand, "Theory and development of higher-order CMAC neural networks," IEEE Control Syst. Mag., vol. 12, no. 2, pp. 23-30, Apr. 1992.
35. H. Jiang, C. Quek, and G. S. Ng, "FCMAC-EWS: A bank failure early warning system based on novel localized pattern learning, and semantically associative fuzzy neural network," Expert Syst. Appl. vol. 34, no. 2, pp. 989-1003, 2008.
36. C. Ting and C. Quek, "TSK-FCMAC: A novel fuzzy CMAC based on the zero-ordered TSK fuzzy inference scheme," 2008, to be published.
37. J. Sim, W. L. Tung, and C. Quek, "FCMAC-Yager: A novel Yager inference scheme based fuzzy CMAC," IEEE Trans. Neural Netw., vol. 17, no. 6, pp. 1394-1410, Nov. 2006.
38. M. N. Nguyen, D. Shi, and C. Quek, "FCMAC-BYY: Fuzzy CMAC using Bayesian Ying-Yang learning," IEEE Trans. Syst. Man Cybern. B, Cybern., vol. 36 no. 5, pp. 1180-1190 Oct. 2006.
39. C. Quek and Z. Guo, "FCM-AARS: A fuzzy cerebellar model network based on the approximate analogical reasoning schema," Pattern Recognit. 2007, submitted for publication.
40. J. F. Medina and M. D. Mauk, "Simulations of cerebellar motor learning: Computational analysis of plasticity at the mossy fiber to deep nucleus synapse," J. Neurosci., vol. 19, no. 16, pp. 7140-7151, 1999.
41. P. M. Steele and M. D. Mauk, "Inhibitory control of LTP and LTD: Stability of synapse strength," J. Neurophysiol., vol. 81, no. 4, pp. 1559-1566, 1999.
42. J. A. Kleim, M. A. Pipitone, C. Czerlanis, and W. T. Greenough, "Structural stability within the lateral cerebellar nucleus of the rat following complex motor learning," Neurobiol. Learn. Memory, vol. 69, pp. 290-306, 1998.
43. J. S. Albus, "Mechanisms of planning and problem solving in the brain," Math. Biosci., vol. 45, pp. 247-293, 1979.
44. Z. Q. Wang, J. L. Schiano, and M. Ginsberg, "Hash-coding in CMAC neural networks," in Proc. IEEE Int. Conf. Neural Netw., 1996, vol. 3, pp. 1698-1703.
45. Z. Luo, Z. Zhao, and C. Zhu, "The unfavorable effects of hash coding on CMAC convergence and compensatory measure," in Proc. IEEE Int. Conf. Intell. Process. Syst., 1997 pp. 419-422.
46. Y. P. Hsu, K. S. Hwang, C. Y. Pao, and J. S. Wang;, "A new CMAC neural network architecture and its ASIC realization," in Proc. Asia South Pacific Design Autom. Conf., 2000, pp. 481-484.
47. Y. P. Hsu, K. S. Hwang, and J. S. Wang;, "An associative architecture of CMAC for mobile robot motion control," J. Inf. Sci. Eng., vol. 18, pp. 145-161, 2002.
48. K. D. Federmeier, J. A. Kleim, and W. T. Greenough, "Learning-induces multiple synapse formation in rat cerebellar cortex, Neurosci. Lett. vol. 332, pp. 180-184, 2002.
49. W. T. Thach, "What is the role of the cerebellum in motor learning and cognition?," Trends Cogn. Sci., vol. 27, no. 9, pp. 331-337, 1998.
50. F. A. Middleton and P. L. Strick, "Cerebellar output: Motor and cognitive channels, Trends Cogn. Sci., vol. 27, no. 9, pp. 348-354, 1998.
51. E. R. Kandel, J. H. Schwartz, and T. M. Jessell, Principles of Neural Science, 4th ed. New York: McGraw-Hill, 2000.
52. T. Tyrrell and D. Willshaw, "Cerebellar cortex: Its simulation and the relevance of Marr's theory," Philosophical Trans.: Biol. Sci., vol. 336, no. 1277, pp. 239-257, 1992.
53. K. Doya, "What are the computations of the cerebellum, the basal ganglia and the cerebral cortex?," Neural Netw., vol. 12, pp. 961-974, 1999.
54. J. Voogd and M. Glickstein, "The anatomy ot the cerebellum," Trends Cogn. Sci., vol. 2, no. 9, pp. 307-313, 1998.
55. P. Strata and F. Rossi, "Plasticity of the olivocerebellar pathway," Trends Neurosci., vol. 21, pp. 407-413, 1998.
56. M. S. Salman, "The cerebellum: It's about time! but timing is not everything - New insights into the role of the cerebellum in timing motor and cognitive tasks., J. Child Neurol., vol. 17, no. 1, pp. 1-9, 2002.
57. M. Rapoport, R. van Reekum, and H. Mayberg, "The role of the cerebellum in cognition and behavior," J. Neuropsychiatry Clin. Neurosci., vol. 12, pp. 193-198, 2000.
58. J. S. Albus, "A theory of cerebellar function," Math Biosci., vol. 10, no. 1, pp. 25-61, 1971.
59. D. Marr, "A theory of cerebellar cortex," J. Physiol. London, vol. 202, pp. 437-470, 1969.
60. M. Ito, The Cerebellum and Neural Control. New York: Raven, 1984.
61. J. C. Houk, J. T. Buckingham, and A. G. Barto, "Models of the cerebellum and motor learning," Behav. Brain Sci., vol. 19, no. 3, pp. 368-383, 1996.
62. M. Ito, "Mechanisms of motor learning in the cerebellum," Brain Res., vol. 886, pp. 237-245, 2000.
63. E. D. Schutter, "A new functional role for cerebellar long term depression," Progr. Brain Res., vol. 114, pp. 529-542, 1997.
64. J. A. Kleim, E. Lussnig, E. R. Schwars, T. A. Comery, and W. T. Greenough, "Synaptogenesis and FOS expression in the motor cortex of the adult rat after motor skill learning," J. Neurosci., vol. 16, no. 14, pp. 4529-4535, 1996.
65. J. A. Kleim, R. A. Swain K. A. Amstrong, R. M. A. Napper, T. A. Jones, and W. T. Greenough, "Selective synaptic plasticity within the cerebellar cortex following complex motor skill learning," Neurobiol. Learn. Memory, vol. 69, pp. 274-289, 1998.
66. J. S. Albus, Brains, Behavior and Robotics. New York: McGraw-Hill, 1981.
67. S. D. Teddy, "State-of-the-art CMACs: A literature survey," Cntr. Comput. Intell., Schl. Comput. Eng., Nanyang Technol. Univ., Nanyang, Singapore, Tech. Rep. C2i-TR-06/009, 2006.
68. K. Ang and C. Quek, "Stock trading using PSEC and RSPOP: A novel evolving rough set-based neuro-fuzzy approach," Proc. IEEE Congr. Evolut. Comput., vol. 2, pp. 1032-1039, 2005.
69. T. Kohonen, Self-Organization and Associative Memory, 3rd ed. Berlin, Germany: Springer-Verlag, 1989.
70. M. Ester, H.-P. Kriegel, J. Sander, and X. Xu, "A density-based algorithm for discovering clusters in large spatial databases with noise," in Proc. 2nd Int. Conf. Knowl. Disc. Data Mining, 1996, pp. 226-231.
71. S. D. Teddy, "The MPSEC density-based clustering algorithm for nonlinear memory assignment in the PSECMAC network," Cntr. Comput. Intell., Schl. Comput. Eng., Nanyang Technol. Univ., Singapore, Tech. Rep. C2i-TR-06/006, 2006.
72. S. J. Orfanidis, Introduction to Signal Processing. Englewood Cliffs, NJ: Prentice-Hall, 1995.
73. B. Widrow and S. D. Stearns, Adaptive Signal Processing. Englewood Cliffs, NJ: Prentice-Hall, 1985.
74. S. D. Teddy, "The PSECMAC neural correlates," Cntr. Comput. Intell., Schl. Comput. Eng., Nanyang Technol. Univ., Singapore, Tech. Rep. C2i-TR-06/007, 2006.
75. 0-FCMAC: A novel fuzzy CMAC based on the zero-ordered TSK fuzzy inference scheme," Cntr. Comput. Intell., Schl. Comput. Eng., Nanyang Technol. Univ., Singapore, Tech. Rep. C21-TR-04/0003, 2004.
76. S. D. Teddy, "The PSECMAC learning convergence," Cntr. Comput. Intell., Schl. Comput. Eng., Nanyang Technol. Univ., Singapore, Tech. Rep. C2i-TR-06/008, 2006.
77. W. L. Tung and C. Quek, "GenSoFNN: A generic self-organizing fuzzy neural network," IEEE Trans. Neural Netw., vol. 13, no. 5, pp. 1075-1086, Sep. 2002.
78. K. K. Ang and C. Quek, "RSPOP: Rough set-based pseudo outer-product fuzzy rule identification algorithm," Neural Comput., vol. 17, no. 1, pp. 205-243, 2005.
79. R. Kohavi, "The power of decision tables." in Lecture Notes in Artificial intelligence, ser. 914, N. Lavrac and S. Wrobel, Eds. Berlin, Germany: Springer-Verlag, 1995, pp. 174-189.
80. University of Waikato, "WEKA 3: Data mining software in JAVA," Waikato, New Zealand [Online]. Available: Http://www.cs.waikato.ac.nz/ml/ weka/
81. D. M. Chance, An Introduction to Derivativs & Risk Management, 6th ed. Mason, OH: Thomson South-Western, 2004.
82. L. T. Nielson Pricing and Hedging of Derivative Securities - Textbook in Continuous-Time Finance Theory. Oxford, U.K.: Oxford Univ. Press, 1999.
83. F. Black and N. Scholes, "The pricing of options and corporate liabilities," J. Politic. Economy, vol. 81, pp. 617-659, 1973.
84. R. J. R. Jr and B. J. Bartter, "Two-state option pricing," J. Finance, vol. 34. pp. 1093-1110, 1979.
85. P. Radzikowski, "Non-parametric methods of option pricing," in Proc. Informs-Korms Conf., 2000, pp. 474-480.
86. H. Amilon, "A neural network versus Black-Scholes: A comparison of pricing and hedging performances," Scandinavian Working Papers in Economics, 2001, Lund Univ. series, Dept. Econom., Lund, Sweden.
87. U. Anders, O. Korn, and C. Schmitt, "Improving the pricing of options - A neural network approach," J. Forecast., vol. 17, no. 5-6, pp. 369-388, 1998.
88. M. Qi and G. S. Maddala, "Option-pricing using artificial neural networks: The case of 500 index call options," Neural Netw. Financial Eng., pp. 78-92, 1995.
89. C. Keber, "Option pricing with the genetic programming approach," J. Comput. Intell. Finance, vol. 7, no. 6, pp. 26-36, 1999.
90. Y. Ait-Sahalia and A. W. Lo, "Nonparametric estimation of state-price densities implicit in financial asset price," MIT Sloan Schl. Manag., Cambridge, MA, LFE-1024-95, 1995.
91. W. L. Tung and C. Quek, "GenSo-OPATS: A brain-inspired dynamically evolving option pricing model and arbitrage trading system," in Proc. IEEE Congr. Evol. Comput., Edinburgh, Scotland, 2005, vol. 3, pp. 2429-2436.
92. Univ. Chicago, "Mercantile Exchange" [Online] Available: Http:// www.cme.com
93. W. L. Tung and C. Quek, "GenSo-FDSS: A neural-fuzzy decision support system for pediatric all cancer subtype identification using gene expression data," Artif Intell. Med., vol. 336, no. 1, pp. 61-88, 2005.
94. J. Shikey, Jr., "A multivariate statistical analysis of the characteristics of problem banks," J. Finance, vol. 1, pp. 21-36, 1975.
95. D. Martin, "Early warning of bank failure: A logistic regression approach," J. Banking Finance, vol. 1, no. pp. 249-276, 1977.
96. R. Cole and J. Gunther, "Separating the likelihood and timing of bank failure. J. Banking Finance, vol. 19, no. 6, pp. 1073-1089, 1995.
97. P. Y. K. Cheng, "Predicting bank failures: A comparison of the cox proportional hazards model and the time varying covariates model," Ph.D. dissertation, Nanyang Business Schl., Nanyang Technol. Univ., Nanyang, Singapore, 2002.
98. Repository for Bank Data" Federal Reserve Bank of Chicago [Online]. Available: Http://www.chicagofed.org
99. W. L. Tung, C. Quek, and P. Y. K. Cheng, "GenSo-EWS: A novel neural-fuzzy based early warning system for predicting bank failures," Neural Netw., vol. 17, no 4, pp. 567-587, 2004.
100. F. M. Ashcroft and S. J. H. Ashcroft, Insulin: Molecular Biology to Pathology. Oxford, U.K.: Oxford Univ. Press, 1992.
101. Glucosim: A Web-Based, Educational Simulation Package for Glucose-Insulin Levels in the Human Body" Illinois Inst. Technol. [Online]. Available: Http://216.47.139.198/glucosim/gsimul.html
102. Health Promotion Board Singapore [Online]. Available: Http:// www.hpb.gov.sg
103. Cntr. Comput. Intell., Schl. Comput. Eng., Nanyang Technol. Univ., C2i-VVeb, Singapore [Online]. Avaiiabie: Http://www.c2i.ntu.edu.sg
104. S. D. Teddy E. M.-K. T, Lai, and C Quek, "Hierarchically clustered adaptive quantization CMAC and its learning convergence," IEEE Trans. Neural Netw., vol. 18, no. 6, pp. 1658-1682, Nov. 2007.
105. W. L. Tung and C. Quek, "Falcon: Neuro fuzzy control and decision systems using FKP and PFKP clustering algorithms," IEEE Trans. Syst. Man Cybern. B, Cybern., vol. 34, no. 1, pp. 686-695, Feb. 2004.
106. R. W. Zhou and C. Quek, "Antilorgery: A novel pseudo-outer product based fuzzy neural network driven signature verification system," Pattern Recognit. Lett., vol. 230, no. 14, pp. 1795-1816, 2002.
107. C. Onek, B. Tan, and V. Sagar, "POPFNN-based fingerprint verification system," Neutral Netw., vol. 14, pp. 305-323, 2001.
108. K. Ouah and C. Ouek, "Maximum reward reinforcement learning: A non-cummulative reward criterion," Expert Syst. Appl., vol. 31, no. 2 pp. 352-359, 2006.
109. K. K. Ang and C. Quek, "Stocvk trading using RSPOP: A novel rough set based neuro-fuzzy approach," IEEE Trans. Neural Netw., vol. 17, no 5, pp. 1101-1315, Sep 2006.