Analysis of the ReSuMe learning process for spiking neural networks

• Autorzy: Filip Ponulak
• Języki publikacji: EN

Abstrakty

EN

In this paper we perform an analysis of the learning process with the ReSuMe method and spiking neural networks (Ponulak, 2005; Ponulak, 2006b). We investigate how the particular parameters of the learning algorithm affect the process of learning. We consider the issue of speeding up the adaptation process, while maintaining the stability of the optimal solution. This is an important issue in many real-life tasks where the neural networks are applied and where the fast learning convergence is highly desirable.

Słowa kluczowe

EN

supervised learning; spiking neural networks; parametric analysis; learning window

• Wydawca: University of Zielona Gora Press
• Czasopismo: International Journal of Applied Mathematics and Computer Science
• Rocznik: 2008
• Tom: 18
• Numer: 2
• Strony: 117-127

Daty

wydano

2008

otrzymano

2007-07-10

poprawiono

2007-11-22

Twórcy

autor

Filip Ponulak

• Institute of Control and Information Engineering, Poznań University of Technology, ul. Piotrowo 3a, 60-965 Poznań, Poland

Bibliografia

• Bi G.-Q. (2002). Spatiotemporal specificity of synaptic plasticity: Cellular rules and mechanisms, Biological Cybernetics 87: 319-332.
• CSIM (2002). CSIM: A neural circuit SIMulator. The IGI LSM Group, Technical University, Graz, http://www.lsm.tugraz.at.
• Freeman J. A. and Skapura D. M. (1991). Neural Networks Algorithms, Applications, and Programming Techniques, Addison-Wesley, Redwood City, CA.
• Gerstner W. and Kistler W. (2002a). Mathematical formulations of Hebbian learning, Biological Cybernetics 87(5-6): 404-415.
• Hertz J., Krogh A. and Palmer R. (1991). Introduction to the Theory of Neural Networks, Addison-Wesley, Redwood City, CA.
• Gerstner W. and Kistler W. (2002b). Spiking Neuron Models. Single Neurons, Populations, Plasticity, Cambridge University Press, Cambridge.
• Kangas J. and Kohonen T. (1996). Developments and applications of the self-organizing map and related algorithms, Mathematics and Computers in Simulation 41(1): 3-12(10).
• Kasiński A. and Kraft M. (2006). The design of a compact LIFneuron circuit in FPGA to enable implementation of largescale spiking neuron networks with learning capabilities, Proceesings of the International Conference on Artificial Intelligence and Soft Computing, ICAISC'2006, Warsaw, Poland, pp. 57-64.
• Kasiński A. and Ponulak F. (2005). Experimental demonstration of learning properties of a new supervised learning method for the spiking neural networks, Lecture Notes in Computer Science, Vol. 3696, pp. 145-153.
• Kempter R., Gerstner W. and van Hemmen J. L. (1999). Hebbian learning and spiking neurons, Physical Review E 59(4): 4498-4514.
• Korbicz J., Obuchowicz A. and Uciński D. (1994). Artificial Neural Networks: Foundations and Applications, Akademicka Oficyna Wydawnicza PLJ, Warsaw. (in Polish).
• Kraft M., Kasiński A. and Ponulak F. (2006). Design of the spiking neuron having learning capabilities based on FPGA circuits, Proceedings of the 3rd International IFAC Workshop on Discrete-Event System Design, Rydzyna, Poland, pp. 301-306.
• Maass W. and Bishop C. (Eds.) (1999). Pulsed Neural Networks, The MIT Press, Cambridge, M.A.
• Maass W., Natschlaeger T. and Markram H. (2002). Real-time computing without stable states: A new framework for neural computation based on perturbations, Neural Computation 14(11): 2531-2560.
• Markram H., Luebke J., Frotscher M. and Sakmann B. (1997). Regulation of synaptic efficacy by coincidence of postsynaptic APs and EPSPs, Science 275(5297): 213-215.
• Natschlaeger T., Maass W. and Markram H. (2002). The “liquid computer”, a novel strategy for real-time computing on time series, Foundations of Information Processing of TELEMATIK 8(1): 32-36.
• Papik K., Molnar B., Schaefer R., Dombovari Z., Tulassay Z. and Feher J. (1998). Application of neural networks in medicine-A review, Medical Science Monitor 4(3): 538-546.
• Ponulak F. (2005). ReSuMe-New supervised learning method for Spiking Neural Networks, Technical Report, Institute of Control and Information Engineering, Poznań University of Technology. Available at http://d1.cie.put.poznan.pl/~fp/.
• Ponulak F. (2006a). ReSuMe-Proof of convergence, Technical Report, Institute of Control and Information Engineering, Poznan University of Technology. Available at http://d1.cie.put.poznan.pl/~fp/.
• Ponulak F. (2006b). Supervised Learning in Spiking Neural Networks with ReSuMe Method, Ph.D. thesis, Institute of Control and Information Engineering, Poznań University of Technology. Available at: http://d1.cie.put.poznan.pl/~fp/.
• Ponulak F., Belter D. and Kasiński A. (2006). Adaptive central pattern generator based on spiking neural networks, Proceedings of EPFL LATSIS Symposium 2006, Dynamical Principles for Neuroscience and Intelligent Biomimetic Devices, Lausanne, Switzerland, pp. 121-122.
• Ponulak F. and Kasiński A. (2005). A novel approach towards movement control with spiking neural networks, Proceedings of the 3rd International Symposium on Adaptive Motion in Animals and Machines, Ilmenau, Germany. (Abstract).
• Ponulak F. and Kasiński A. (2006a). Generalization Properties of SNN Trained with ReSuMe, Proceedings of the European Symposium on Artificial Neural Networks, ESANN'2006, Bruges, Belgium, pp. 623-629.
• Ponulak F. and Kasiński A. (2006b). ReSuMe learning method for spiking neural networks dedicated to neuroprostheses control, Proceedings of EPFL LATSIS Symposium 2006, Dynamical Principles for Neuroscience and Intelligent Biomimetic Devices, Lausanne, Switzerland, pp. 119-120.
• van Hemmen J. (2001). Theory of synaptic plasticity, in F.Moss and S.Gielen (Eds.), Handbook of Biological Physics, Neuro-informatics, Neural Modelling, Elsevier, Amsterdam, Vol. 4, pp. 771-823.

Identyfikatory

DOI

10.2478/v10006-008-0011-1