Abstract
The CMAC neural network is a well-established computational model of the human cerebellum. A major advantage is its localized generalization property which allows for efficient computations. However, there are also two major problems associated with this localized associative property. Firstly, it is difficult to fully-train a CMAC network as the training data has to fully cover the entire set of CMAC memory cells. Secondly, the untrained CMAC cells give rise to undesirable network output when presented with inputs that the network has not previously been trained for. To the best of the authors’ knowledge, these issues have not been sufficiently addressed. In this paper, we propose a neuropsychologically-inspired computational approach to alleviate the above-mentioned problems. Motivated by psychological studies on human motor skill learning, a ”patching” algorithm is developed to construct a plausible memory surface for the untrained cells in the CMAC network. We demonstrate through the modeling of the human glucose metabolic process that the ”patching” of untrained cells offers a satisfactory solution to incomplete training in CMAC.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Middleton, F.A., Strick, P.L.: The cerebellum: An overview. Trends in Cognitive Sciences 27(9), 305–306 (1998)
Albus, J.S.: Marr and Albus theories of the cerebellum two early models of associative memory. In: Proc. IEEE Compcon. (1989)
Albus, J.S.: A theory of cerebellar function. Math. Biosci. 10(1), 25–61 (1971)
Kandel, E.R., Schwartz, J.H., Jessell, T.M.: Principles of Neural Science, 4th edn. McGraw-Hill, New York (2000)
Marr, D.: A theory of cerebellar cortex. J. Physiol. London 202, 437–470 (1969)
Albus, J.S.: A new approach to manipulator control: The Cerebellar Model Articulation Controller (CMAC). J. Dyn. Syst. Meas. Control, Trans. ASME, 220–227 (1975)
Albus, J.S.: Data storage in Cerebellar Model Articullation Controller (CMAC). J. Dyn. Syst. Meas. Control, Trans. ASME, 228–233 (1975)
Yamamoto, T., Kaneda, M.: Intelligent controller using CMACs with self-organized structure and its application for a process system. IEICE Trans. Fundamentals 82(5), 856–860 (1999)
Wahab, A., Tan, E.C., Abut, H.: HCMAC amplitude spectral subtraction for noise cancellation. In: Intl. Conf. Neural Inform. Processing (2001)
Huang, K.L., Hsieh, S.C., Fu, H.C.: Cascade-CMAC neural network applications on the color scanner to printer calibration. In: Intl. Conf. Neural Networks, vol. 1, pp. 10–15 (1997)
Miller, W.T., Glanz, F.H., Kraft, L.G.: CMAC: An associative neural network alternative to backpropagation. Proc. IEEE 78(10), 1561–1657 (1990)
Tomporowski, P.D.: The Psychology of Skill: A life-Span Approach. Praeger, Westport CT (2003)
Mazur, J.E.: Learning and Behavior. Pearson/Prentice Hall (2006)
Scheidt, R.A., Dingwell, J.B., Mussa-Ivaldi, F.A.: Learning to move amid uncertainty. Journal of Neurophysiology 86, 971–985 (2001)
Lam, T., Dietz, V.: Transfer of motor performance in an obstacle avoidance task to different walking conditions. Journal of Neurophysiology 92, 2010–2016 (2004)
Chen, Y., et al.: The interaction of a new motor skill and an old one: H-reflex conditioning and locomotion in rats. Journal of Neuroscience 25(29), 6898–6906 (2005)
Houk, J.C., Buckingham, J.T., Barto, A.G.: Models of the cerebellum and motor learning. Behavioral and Brain Sciences 19(3), 368–383 (1996)
Tyrrell, T., Willshaw, D.: Cerebellar cortex: Its simulation and the relevance ofMarr’s theory. Philosophical Transactions: Biological Sciences 336(1277), 239–257 (1992)
Widrow, B., Stearns, S.D.: Adaptive Signal Processing. Prentice-Hall, Englewood Cliffs (1985)
Palmer, C., Meyer, R.K.: Conceptual and motor learning in music performance. Psychological Science 11(1), 63–68 (2000)
Weigelt, C., et al.: Transfer of motor skill learning in association football. Ergonomics 43(10), 1698–1707 (2000)
Fletcher, L., et al.: Feasibility of an implanted, closed-loop, blood-glucose control device. Immunology 230 (2001)
Schetky, L.M., Jardine, P., Moussy, F.: A closed loop implantable artificial pancreas using thin film nitinol mems pumps. In: Proceedings of International Conference on Shape Memory and Superelastic Technologies, SMST 2003 (2003)
Sorensen, J.T.: A Physiologic Model of Glucose Metabolism in Man and its Use to Design and Assess Improved Insulin Therapies for Diabetes. PhD thesis, Departement of Chemical Engineering, MIT (1985)
Illinois Institute of Technology: GlucoSim: A web-based educational simulation package for glucose-insulin levels in the human body, Online, http://216.47.139.198/glucosim/gsimul.html
Health Promotion Board Singapore, Online, http://www.hpb.gov.sg
Tung, W.L., Teddy, S.D., Zhao, G.: Neuro-cognitive approaches to the control and regulation of insulin for the treatment of diabetes mellitus. Phase 1: Neurologically inspired modeling of the human glucose metabolic process. Technical Report C2i-TR-05/002, Center for Computational Intelligence, School of Computer Engineering, Nanyang Technological University, Singapore (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Teddy, S.D., Lai, E.M.K., Quek, C. (2006). A Neuropsychologically-Inspired Computational Approach to the Generalization of Cerebellar Learning. In: King, I., Wang, J., Chan, LW., Wang, D. (eds) Neural Information Processing. ICONIP 2006. Lecture Notes in Computer Science, vol 4232. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11893028_18
Download citation
DOI: https://doi.org/10.1007/11893028_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-46479-2
Online ISBN: 978-3-540-46480-8
eBook Packages: Computer ScienceComputer Science (R0)