Abstract
What it means to “solve problems in a scientific way” changes in history. It had taken a long time for the paradigm of the “rigid” — the “objective”, the “clare et distincte” — to become precise (and hence fixed, in the ambivalent sense of such progress): as being identical with “formalized” or “formalizable”, thus referring to a given deductive apparatus. This appears convincing. In order to be rigid in the sense that anybody else (sufficiently trained) might understand my words and symbols as they were meant, I have to fix the language and the rules of operating on symbols beforehand, and all that “meaning” means must be contained in that initial ruling. What other way could there be to definitely exclude subjective misunderstanding and failure of any kind?
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bellman, R. E. (1957): Dynamic Programming (Princeton University Press, Princeton, New York)
Braun, H. (1994): Evolution — a Paradigm for Constructing Intelligent Agents, Proceedings of the ZiF-FG Conference Prerational Intelligence — Phenomenology of Complexity Emerging in Systems of Simple Interacting Agents
Braun, H. (1995): On optimizing large neural networks (multilayer perceptrons) by learning and evolution. International Congress on Industrial and Applied Mathematics ICIAM 1995. Also to be published in Zeitschrift für angewandte Mathematik und Mechanik ZAMM
Braun, H., Feulner, J., and Ragg, Th. (1995): Improving temporal difference learning for deterministic sequential decision problems International Conference on Artificial Neural Networks (ICANN 1995), (Paris, E2 and Cie) pp. 117–122
Braun, H., Landsberg, H. and Ragg, Th. (1996): A comparative study of neural network optimization techniques, Submitted to ICANN
Ebcioglu (1986): An expert system for harmonization of chorales in the style of J. S. Bach, Ph.D. thesis, State University of New York (Buffalo N.Y.)
Feulner, J. and Hörnel, D. (1994): MELONET: Neural networks that learn harmonybased melodic variations, in: Proceedings of the International Computer Music Conference (ICMC) (International Computer Music Association, Arhus)
Gutjahr, St. (1997): Improving neural prediction systems by building independent committees, Proceedings of the fourth International Conference on Neural Networks in the Capital Market (Pasadena, USA)
Gutjahr, St., Riedmiller, M. and Klingemann, J. (1997): Daily prediction of the foreign exchange rate between the US dollar and the German mark using neural networks, The Joint 1997 Pacific Asian Conference on Expert Systems/Singapore International Conference on Intelligent Systems (1997)
Hörnel, D. and Degenhardt, P. (1997): A neural organist improvising baroque-style melodic variations, Proceedings of the International Computer Music Conference (ICMC) (International Computer Music Association, Thessaloniki)
Hammer, M. and Menzel, R. (1995): Learning and memory in the honeybee, J. Neuroscience 15, pp. 1617–1630
Hertz, J., Krogh, A., and Palmer, R. (1991): Introduction to the Theory of Neural Computation (Addison-Wesley, New York)
Hild, H., Feulner J. and Menzel, W. (1992): HARMONET: A neural net for harmonizing chorals in the style of J. S. Bach, in: Advances in Neural Information Processing 4 (NIPS4), pp. 267–274
Janusz, B. and Riedmiller, M. (1996): Self-learning neural control of a mobile robot, to appear in: Proceedings of the IEEE ICNN 1995 (Perth, Australia)
Malaka, R. (1996): Neural Information processing in insect olfactory systems, Doctoral dissertation (Karlsruhe)
Malaka, R. (1996): Do the antennal lobes of insects compute principal components?, Submitted to: World Congress on Neural Networks ‘96 (San Diego)
Malaka, R., Ragg, Th., and Hammer, M. (1995): Kinetic models of odor transduction implemented as artificial neural networks — simulations of complex response properties of honeybee olfactory neurons, Biol. Cybern., 73, pp. 195–207
Malaka, R., Schmitz, St., and Getz, W. (1996): A self-organizing model of the antennal lobes, Submitted to the 4th International Conference on Simulation of Adaptive Behaviour, SAB
Menzel, R., Hammer, M., and U. Miller(1995): Die Biene als Modellorganismus für Lern- und Gedächtnisstudien, Neuroforum 4, pp. 4–11
Riedmiller, M. (1993): Controlling an inverted pendulum by neural plant identification, Proceedings of the IEEE International Conference on Systems, Man and Cybernetics (Le Touquet, France)
Riedmiller, M. (1994): Advanced supervised learning in multi-layer perceptrons — From backpropagation to adaptive learning algorithms, Computer Standards and Interfaces 16, pp. 265–278
Riedmiller, M. (1996): Learning to control dynamic systems, to appear in: Proceedings of the European Meeting on Cybernetics and Systems Research (EMCSR 1996) (Vienna)
Riedmiller, M. (1997): Selbständig lernende neuronale Steuerungen, Dissertation Karlsruhe 1996, Fortschrittberichte VDI-Verlag (Düsseldorf)
Riedmiller, M. and Braun, H. (1993): A direct adaptive method for faster backpropagation learning: The RPROP algorithm, Proceedings of the IEEE International Conference on Neural Networks (ICNN) (San Francisco), pp. 586–591
Sutton, R. S. (1988): Learning to predict by the methods of temporal differences, Machine Learning, 3, pp. 9–44
Watkins, C. J. (1989): Learning from delayed rewards, Ph.D. thesis, Cambridge University.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Menzel, W. (1998). Problem Solving with Neural Networks. In: Ratsch, U., Richter, M.M., Stamatescu, IO. (eds) Intelligence and Artificial Intelligence. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-03667-9_9
Download citation
DOI: https://doi.org/10.1007/978-3-662-03667-9_9
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-08358-7
Online ISBN: 978-3-662-03667-9
eBook Packages: Springer Book Archive