Abstract
Vertical information processing, including multi-level and multi-scale processing, plays an important role in biological systems since hierarchical structures might support learning and stability of the systems. The power of a vertical information processing system is more than the addition of the contribution of each constituting element together. Moreover, it means that the interactions of elements produce a synergistic effect that is greater than the sum of the individual elements. We have developed a coevolving computer model, motivated from physiological evidence, that integrates intra and interneuronal information processing, subjected to six levels of evolution. Information processing at the intraneuronal levels is to create a repertoire of pattern processing neurons. Information processing at the interneuronal levels is to group appropriate pattern processing neurons to constitute an effective pattern processing system. Evolutionary learning algorithms have been applied to each mode alternately. The system was tested with two sets of 1000 patterns. The experimental result shows that the system effectively employs synergy among different levels of information processing to obtain pattern differentiation capability. It also shows that synergies occur only when individual elements work with each other in a selectively cooperative manner.
Preview
Unable to display preview. Download preview PDF.
References
Chen, J.-C., A synergetic multilevel artificial brain for pattern categorization/neurocontrol. Proceedings of the Sixth International Conference on Molecular Electronics and Biocomputing, Okinawa, Japan (1995) 247–250.
Chen, J.-C., Simulation of a discrete-event brain-Like computer model in pattern recognition/neurocontrol. Proceedings of the 1996 Summer Computer Simulation Conference, V.W. Ingalls, J. Cynamon, and A.V. Saylor (eds.) (Simulation Councils, Inc., San Diego, CA) (1996a) 193–198.
Chen, J.-C., Adaptive pattern recognition with a self-organizing learning architecture. Proceedings of 1996 International Computer Symposium, Kaohsiung, Taiwan (1996b) 152–159.
Chen, J.-C. and Conrad, M., Learning synergy in a multilevel neuronal architecture. Biosystems, 32 (1994a) 111–142.
Chen, J.-C. and Conrad, M., A multilevel neuromolecular architecture that uses the extradimensional bypass principle to facilitate evolutionary learning. Physica D., 75 (1994b) 417–437.
Chen, J.-C. and Conrad, M., Multilevel evolutionary learning in an artificial neuromolecular brain and its application to the categorization of Chinese characters. Evolutionary Programming V, L.J. Fogel, P.J. Angeline, and T. Back (eds.) (M.I.T. Press, Cambridge, MA) (1996) 189–196.
Chen, J.-C. and Conrad, M., Pattern categorization and generalization with a virtual neuromolecular architecture. Neural Networks (in press) (1997a).
Chen, J.-C. and Conrad, M., Evolutionary learning with a neuromolecular architecture: a biological motivated approach to computational adaptability. Soft Computing Research Journal (in press) (1997b).
Conrad, M., Evolutionary learning circuits. J. Theoret. Biol. 46 (1974) 167–188.
Conrad, M., Complementary molecular models of learning and memory. Biosystems 8 (1976a) 119–138.
Conrad, M., Molecular information structures in the brain. J. Neurosci. Res. 2 (1976b) 233–254.
Hameroff, S.R. and Watt, R.C., Information processing in microtubules. J. Theor. Biol., 98 (1982) 549–561.
Liberman, E.A., Minina, S.V., Shklovsky-Kordy, N.E., and Conrad, M., Microinjection of cyclic nucleotides provides evidence for a diffusional mechanism of intraneuronal control. Biosystems, 15 (1982) 127–132.
Matsumoto, G., Tsukita, S., and Arai, T., Organization of the axonal cytoskeleton: differentiation of the microtubule and actin filament arrays. Cell Movement, Vol. 2: Kinesin, Dynein, and Microtubule Dynamics, F.D. Warner and J.R. McIntosh (eds.) (Alan R Liss, New York) (1989) 335–356.
Werbos, P., The cytoskeleton: why it may be crucial to human learning and to neurocontrol. Nanobiology, 1 (1992) 75–95.
Wolfram, S., Cellular automata as models of complexity. Nature 311 (1984) 419–424.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chen, JC. (1997). Computational and learning synergies with a coevolving multilevel architecture. In: Yao, X., Kim, JH., Furuhashi, T. (eds) Simulated Evolution and Learning. SEAL 1996. Lecture Notes in Computer Science, vol 1285. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0028522
Download citation
DOI: https://doi.org/10.1007/BFb0028522
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63399-0
Online ISBN: 978-3-540-69538-7
eBook Packages: Springer Book Archive