Abstract
The models of multi-input pulse neuron in generalized vector-matrix form are proposed in order to solve digital signal processing problems. Nonrecursive and recursive digital models are considered. Nonrecursive models use the description of linear systems in a convolution form and the input signal is presented as a sequential or a parallel binary vector. Recursive models are based on the description of linear systems in the time domain and use an impulse response and a state space approaches. A learning rule for the mentioned models of a pulse neuron is derived to solve a problem of signal reconstruction and adaptive noise suppression. Results of a computer simulation are presented.
Keywords
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hen, H.Y., Jenq-Neng, H.: Introduction to neural networks for signal processing. In: Hen, H.Y., Jenq-Neng, H. (eds.) Handbook of Neural Network Signal Processing, pp. 1–30. CRC Press, Boca Raton (2002)
Maass, W.: Paradigms for computing with spiking neurons. In: van Hemmen, J.L., Cowan, J.D., Domany, E. (eds.) Models of Neural Networks. Early Vision and Attention, vol. 4, pp. 373–402. Springer, New York (2002)
Gerstner, W., Kistler, W.M.: Spiking Neuron Models – Single Neurons, Populations, Plasticity. Cambridge University Press, Cambridge (2002)
Natschlaeger, T., Ruf, B.: Spatial and temporal pattern analysis via spiking neurons. Netw.: Comput. Neural Syst. 9, 319–332 (1998)
Ponulak, F., Kasiński, A.: Introduction to spiking neural networks: information processing, learning and applications. Acta Neurobiol. Exp. 71, 409–433 (2011)
Popkov, Y., Ashimov, A.A., Asaubaev, K.: Statistical Theory of Automatic Systems with Dynamic Pulse-Frequency Modulation. Nauka Publ., Moscow (1988). (in Russian)
Bondarev, V.N.: On system identification using pulse-frequency modulated signals. Research report 88-E-195, Eindhoven University of Technology, Eindhoven (1988)
Wei, D., Harris, J.G.: Signal reconstruction from spiking neuron models. In: Proceedings of the 2004 International Symposium on Circuits and Systems (ISCAS 2004), vol. 5, pp. 353–356. IEEE Press (2004)
Bondarev, V.N.: Adaptive pulse-frequency modeling aimed at digital signal processing problems. Vestn. SevGTU 18, 46–51 (1999). (in Russian)
Bondarev, V.N.: Adaptive synthesis of pulse-frequency digital nonrecursive filters. Sbornik nauchnyih trudov AVMS im. P.S. Nahimova 4, 80–85 (2012). (in Russian)
Bondarev, V.N.: Application of digital model of pulse neuron for the adaptive signal filtration. In: Proceedings of the XVII All-Russian Scientific and Technical Conference “Neuroinformatics-2015”, Part II, pp. 169–177. NIYaU MIFI Publ., Moscow (2015). (in Russian)
Bruckstein, A.M., Zeevi, Y.Y.: Analysis of “Integrate-to-Threshold” neural coding schemes. Biol. Cybern. 34, 63–79 (1979)
Widrow, B., Stearns, S.D.: Adaptive Signal Processing. Prentice-Hall, Englewood Cliffs (1985)
Nise, N.S.: Control Systems Engineering, 6th edn. Wiley, Hoboken (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Bondarev, V. (2016). Vector-Matrix Models of Pulse Neuron for Digital Signal Processing. In: Cheng, L., Liu, Q., Ronzhin, A. (eds) Advances in Neural Networks – ISNN 2016. ISNN 2016. Lecture Notes in Computer Science(), vol 9719. Springer, Cham. https://doi.org/10.1007/978-3-319-40663-3_74
Download citation
DOI: https://doi.org/10.1007/978-3-319-40663-3_74
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-40662-6
Online ISBN: 978-3-319-40663-3
eBook Packages: Computer ScienceComputer Science (R0)