350 rub
Journal Neurocomputers №8 for 2010 г.
Article in number:
Learning with teacher of spiking neuron in spatial-temporal impulse pattern detection task
Keywords: spiking neuron neuron models spiking neuron learning information theory information entropy
Authors:
O. Yu. Sinyavskiy, A. I. Kobrin
Abstract:
Methods of learning with the teacher of spiking neurons are investigated in this work. Defining key features of stochastic spiking neurons generalized spiking neuron model is constricted. Introduction of the generalized spiking neuron model allows to conveniently formalize problems of its learning with teacher. Information theory language is used in lsearning problems description. Specifically, learning of spiking neuron with the teacher problem is solved using information entropy minimization algorithm. Examples of entropy minimization algorithm are provided for concrete model of spiking neuron extended from Spike Response Model. The task of time delay maintenance between input and output spikes and task of detecting of spiking pattern in a noisy stream of impulse signals are considered.
Pages: 69-76
References
  1. Мартин Р., Николлс Дж., Валлас Б., Фукс П.От нейрона к мозгу.М.: УРСС. 2003.
  2. Gerstner, W, Kistler, W. M.,Spiking Neuron Models: Single Neurons, Populations, Plasticity.s.l.: Cambridge University Press. 2002.
  3. Perkel, D. H., Feldman, M. W.,Neurotransmitter release statistics: Moment estimates for inhomogeneous Bernoulli trials.Berlin: SpringerBerlin/ Heidelberg. 1979.
  4. Синявский О. Ю., Кобрин А. И. Использование информационных характеристик потока импульсных сигналов для обучения спайковых нейронных сетей // Интегрированные модели и мягкие вычисления в искусственном интеллекте (28-30 мая 2009 г.): Сб. научн. тр. 2009. Vol. 2.
  5. Pfister, J. P., Toyoizumi T., Barber, D., Gerstner, W., Optimal Spike-Timing Dependent Plasticity for Precise Action Potential Firing in Supervised Learning // Neural computation 2006. Vol. 18. 6.
  6. Hebb, D. O.,The Organization of Behavior. New York: John Wiley & Sons. 1949.
  7. Webster, R. A.,Neurotransmitters. Drugs and Brain Function. s.l.: John Wiley and Sons. 2002.
  8. Осовский С.Нейронные сети для обработки информации. М.: Финансы и статистика. 2002.
  9. Стратонович Р. Л.Теория информации.М.: Сов. радио. 1975.
  10. Bugmann, G.,Christodoulou, C.,and Taylor, J. G., Role of temporal integration and fluctuation detection in the highly irregular firing of a leaky integrator neuron model with partial reset // Neural Computation. 1997. Vol. 5. 9.
  11. Panchev, C., Wermter, S., Temporal Sequence Detection with Spiking Neurons: Towards Recognizing Robot Language Instruction // Connection Science. 2006. Vol. 18. 1.