Abstract
Based on existing work where categorical and geometrical methods were used to establish a mathematical model of neural net structures, we develop a new very general model for artificial neural networks (ANN), where all basic components of a network are described abstractly. This mathematical model serves as a guideline for design and implementation of a new ANN-simulator. The proposed model of neuron types will be illustrated by the discussion of an example, using the Single Spiking Neuron Model (SSM). The main building blocks of the simulation tool, a new construction principle for ANN, and abstract modeling of connection weights are presented.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
J. M. Bower and D. Beeman. The book of GENESIS: Exploring realistic neural models with the GEnereal SImulation System. Springer-Verlag, NewYork, 1998.
R. Bernhaupt and J. Pfalzgraf. Time Coded Neurons, Geometric Networks and Homomorphic Learning In: Advances in Neural Networks and Applications, pages 268–273. World SES Press, 2001.
A. Delorme, J. Gautrais, R. Rullen, and S. Thorpe. SpikeNET: a simulator for modeling large networks of integrate and fire neurons. Neurocomputing, 26-27:989–996, 1999.
H. Geiger. Optical quality control with selflearning systems using a combination of algorithmic and neural network approaches. Proceedings of the Second European Congress on Intelligent Techniques and Soft Computing, EUFIT’94, Aachen, September 20–23, 1994.
W. Gerstner. The Handbook of Biological Physics, volume 4, chapter 12, pages 447–494. Elsevier Science, 2001.
H. Geiger and J. Pfalzgraf. Quality control connectionist networks supported by a mathematical model. Proceedings of the International Conference on Engineering Applications of Artificial Neural Networks (EANN’95), 21–23 August 1995, Helsinki. A.B. Bulsari, S. Kallio (Editors), Finnish AI Society, 1995.
K. Lang. Single spiking neuronal networks for object recognition. Master’s thesis, Universität Salzburg, Institut für Computerwissenschaften, 2001.
W. Maass and C. M. Bishop. Pulsed Neural Networks. MIT Press, 1999.
J. Pfalzgraf. The concept of logical fiberings and fibered logical controllers. Proceedings CASYS 2000, August 2000, Liege, Belgium, American Institute of Physics, D. M. Dubois (ed.), 2000.
J. Pfalzgraf. A note on modeling connectionist network structures: geometric and categorical aspects. In Proceedings Artificial Intelligence and Symbolic Computation, AISC’2000, July 17–19, 2000, Madrid. Springer Lecture Notes in AI, vol.1930. J. Calmet, E. Roanes (Eds.), 2001.
J. Pfalzgraf. Modeling Connectionist Network Structures: Some Geometric and Categorical Aspects. Annals of Mathematics and AI (to appear), 2002.
J. Pfalzgraf and W. Meixl. A logical approach to model concurrency in multi agent systems. Proceedings EMCSR 2000, April 25–28, Vienna, 2000.
J. Sixt. Design of an artificial neural network simulator and its integration with a robot simulation environment. Master’s thesis, Johannes Kepler University Linz, Institute of Mathematics, 1994.
A. Zell. Simulation Neuronaler Netze. Addison-Wesley, Bonn, 1994.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bernhaupt, R., Pfalzgraf, J. (2002). On Mathematical Modeling of Networks and Implementation Aspects. In: Calmet, J., Benhamou, B., Caprotti, O., Henocque, L., Sorge, V. (eds) Artificial Intelligence, Automated Reasoning, and Symbolic Computation. AISC Calculemus 2002 2002. Lecture Notes in Computer Science(), vol 2385. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45470-5_17
Download citation
DOI: https://doi.org/10.1007/3-540-45470-5_17
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-43865-6
Online ISBN: 978-3-540-45470-0
eBook Packages: Springer Book Archive