MODULAR AND SELF-ORGANIZING CONNECTIONIST SYSTEMS: TOWARD HIGHER LEVEL INTELLIGENT FUNCTIONS

Authors

  • Kurosh Madani

DOI:

https://doi.org/10.47839/ijc.5.2.391

Keywords:

Modularity, Self-Organization, Artificial Intelligent systems, Real-World applications, Implementation

Abstract

Recent advances in “neurobiology” allowed highlighting some of key mechanisms of animal intelligence. Among them one can emphasizes brain’s “modular” structure and its “self-organizing” capabilities. The main goal of this paper is to show how these primary supplies could be exploited and combined in the frame of “soft-computing” issued techniques in order to design intelligent artificial systems emerging higher level intelligent behavior than conventional Artificial Neural Networks (ANN) based structures.

References

A. Hanibal: VLSI building bloc for neural networks with on chip back learning. Neurocomputing, Vol. 5, pp. 25 37, (1993).

A. Krogh and J. Vedelsby: Neural Network Ensembles, Cross Validation and Active Learning, Advances in Neural Information Processing Systems7, pp. 231-238 (1995).

J. Bruske and G. Sommer: Dynamic cell structure. Advances in Neural Information Processing Systems7, pp. 497-504 (1995)

K. K. Sung and P. Niyogi: Active Learning for Function Approximation. Advances in Neural Information Processing Systems7, pp. 593-600 (1995).

K. J. Lang and M. J. Witbrock: Learning to tell two spirals apart. Connectionist Models Summer School, pp. 52-59 (1998).

M. Mayoubi, M. Schafer, S. Sinsel: Dynamic Neural Units for Non-linear Dynamic Systems Identification. LNCS Vol. 930, Springer Verlag, pp.1045-1051, (1995).

Multiple Model Approaches to Modeling and Control, edited by R. Murray-Smith and T.A. Johansen, Taylor & Francis Publishers, ISBN 0-7484-0595-X (1997).

S. Ernst, Hinging hyper-plane trees for approximation and identification, 37th IEEE Conf. on Decision and Control, Tampa, Florida, USA, (1998).

K. Madani, M. Rybnik, A. Chebira: Data Driven Multiple Neural Network Models Generator Based on a Tree-like Scheduler, LNCS series, Edited by: J. Mira, A. Prieto - Springer Verlag, ISBN 3-540-40210-1, pp. 382-389 (2003).

K. Madani, M. Rybnik, A. Chebira, Non Linear Process Identification Using a Neural Network Based Multiple Models Generator, LNCS series, Edited by: J. Mira, A. Prieto - Springer Verlag. ISBN 3-540-40211-X, pp. 647-654 (2003).

Ning Li, S. Y. Li, Y. G. Xi, Multi-model predictive control based on the Takagi-Sugeno fuzzy models: a case study, Information Sciences 165, pp. 247-263 (2004).

K. Madani, L. Thiaw, R. Malti, G. Sow, Multi-Modeling: a Different Way to Design Intelligent Predictors, Lecture Notes in Computer Science (LNCS 3512): “Computational Intelligence and Bio-inspired Systems”, Ed.: J. Cabestany, A. Prieto, and F. Sandoval, Springer Verlag Berlin Heidelberg, ISBN 3-540-26208-3, pp. 976 – 984, June (2005).

K. Madani, L. Thiaw, Self-Organizing Multi-Modeling: a Different Way to Design Intelligent Predictors. Neurocomputing ISSN 0925-2312, 2006. (Under press, to be published at the end of 2006 or at the beginning of 2007).

K. Madani, A. Chebira, D. Langlois, An Artificial Neural Network Based Approach to Mass Biometry Dilemma Taking advantage from IBM ZISC-036 Neuro-Processor Based Massively Parallel Implementation, International Conference on Neural Networks and Artificial Intelligence (ICNNAI 2006), 31 May - 2 June 2006, Brest, Byelorussia, conference proceedings pp. 84-92.

L.M. Reyneri, Weighted Radial Basis Functions for Improved Pattern Recognition and Signal Processing, Neural Processing Let., Vol. 2, No. 3, pp 2-6, May (1995).

G. Tremiolles (de), K. Madani, P. Tannhof, A New Approach to Radial Basis Function’s like Artificial Neural Networks, NeuroFuzzy'96, IEEE European Workshop, Vol. 6 N° 2, pp 735-745, April 16 to 18, Prague, Czech Republic, (1996).

Haykin S., Neural nets. A comprehensive foundation, 2on edition. Ed. Prentice Hall (1999).

M.A. Arbib (ed.), Handbook of Brain Theory and Neural Networks, 2ed. M.I.T. Press. (2003).

ZISC/ISA ACCELERATOR card for PC, User Manual, IBM France, February (1995).

G. De Tremiolles, “Contribution to the theoretical study of neuro-mimetic models and to their experimental validation: a panel of industrial applications”, Ph.D. Report, University of PARIS XII, March 1998 (in French).

G. De Tremiolles, P. Tannhof, B. Plougonven, C. Demarigny, K. Madani, “Visual Probe Mark Inspection, using Hardware Implementation of Artificial Neural Networks, in VLSI Production”, LNCS - Biological and Artificial Computation : From Neuroscience to Technology, Ed.: J. Mira, R. M. Diaz and J. Cabestany, Springer Verlag Berlin Heidelberg, pp. 1374-1383, (1997).

S. Goonatilake and S. Khebbal, “Intelligent Hybrid Systems: Issues, Classification and Future Directions”, in Intelligent Hybrid Systems, John Wiley & Sons, pp 1-20, ISBN 0 471 94242 1.

Madani K., Chebira A., "A Data Analysis Approach Based on a Neural Networks Data Sets Decomposition and it’s Hardware Implementation", PKDD 2000, Lyon, France, 2000.

M. Vukobratovic, B. Borovac. Zero moment point – thirty five years of its live. International Journal of Humanoid Robotics, 2004, Vol.1 N°1, pp. 157-173.

S. Kajita, F. Kaneniro, K. Kaneko, K. Fujiwara, K. Harada, K. Yokoi and H. Hirukawa. Biped walking pattern generation by using preview control of Zero-Moment Point. Proc. IEEE Conf. on Robotics and Automation, 2003, pp. 1620-1626.

Q. Huang, K. Yokoi, S. Kajita, K. Kaneko, H. Arai, N. Koyachi, K. Tanie. Planning walking patterns for a biped robot. IEEE Transactions on Robotics and Automation, 2001, Vol.17, N°3, pp. 280-289.

K. Hirai, M. Hirose, Y. Haikawa, T. Takenaka. The development of honda humanoid robot. Proc. IEEE Conf. on Robotics and Automation, 1998, pp. 1321-1326.

C. Sabourin, O. Bruneau. Robustness of the dynamic walk of a biped robot subjected to disturbing external forces by using CMAC neural networks. Robotics and Autonomous Systems, 2005, Vol.23, pp. 81-99.

C. Sabourin, K. Madani, O. Bruneau, A Fuzzy-CMAC Based Hybrid Intuitive Approach for Biped Robot’s Adaptive Dynamic Walking, ICNNAI 2006 conference proceedings (to be published in June 2006).

J. S. Albus. A new approach to manipulator control: the Cerebellar Model Articulation Controller (CMAC). Journal of Dynamic Systems, Measurement and Control, (1975), pp. 220-227.

J. S. Albus, Data storage in the cerebellar model articulation controller (CMAC), Journal of Dynamic Systems, Measurement and Control, 1975, pp. 228-233.

W. T. Miller, F. H. Glanz, L. G. Kraft, CMAC: An associative neural network alternative to backpropagation, Proceedings of the IEEE, Special Issue on Neural Networks}, vol.78, N°10, 1990, pp. 1561-1567.

C. Chevallereau, G. Abba, Y. Aoustin, F. Plestan, E.R. Westervelt, C. Canudas-de-Wit, J.W. Grizzle. RABBIT: A testbed for advanced control theory. IEEE Control Systems Magazine, 2003, Vol.23, N°5, pp. 57-79.

http://robot-rabbit.lag.ensieg.inpg.fr/.

http://www.laas.fr/robea/

O. Bruneau, F.B. Ouezdou. Distributed ground/walking robot interactions. Robotica, Cambridge University Press, 1999, Vol.17, N°3, pp. 313-323.

Bezdek, J.C. Pattern Recognition with Fuzzy Objective Functions. Plenum Press, N.Y., 1981.

K. Madani, L. Thiaw, Multi-Model based Identification: Application to Nonlinear Dynamic Behavior Prediction, in “Image Analysis, Computer Graphics, Security Systems and Artificial Intelligence Applications”, Ed.: K. Saeed, R. Mosdorf, J. Pejas, O-P. Hilmola and Z. Sosnowski, ISBN 83-87256-86-2, pp. 365-375.

Downloads

Published

2014-08-01

How to Cite

Madani, K. (2014). MODULAR AND SELF-ORGANIZING CONNECTIONIST SYSTEMS: TOWARD HIGHER LEVEL INTELLIGENT FUNCTIONS. International Journal of Computing, 5(2), 6-17. https://doi.org/10.47839/ijc.5.2.391

Issue

Section

Articles