Abstract
The technique presented in this article comes from the formalization of some passive electric properties of the dendritic trees in biological neurons using a complex-valued spatio-temporal coding. The introduction of this coding in the complex-valued neural networks makes it possible to give an algebraic formalization to the spiking neural networks. Our finality in term of applications is the processing of spatio-temporal patterns in the field of human-computer interactions. This technique was thus evaluated by simulation on handwritten character recognition and, audio and visual speech recognition problems. To improve the performances of it we present in this paper a design methodology which helps building multinetwork spiking machines. The implementation of a pen oriented interface made for an industrialist illustrates the method.
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
A. Ardouin and N. Brouard and C. Moreau and R. Plouvier and S. Rouchy and G. Vaucher. Un exemple d’interface orienté stylo à base de STANN. In Journées Neurosciences et Sciences de l’Ingénieur, Sept 2002.
A.R. Baig. Une approche méthodologique de l’utilisation des STAN appliquée à la reconnaissance visuelle de la parole. PhD thesis, Univ. Rennes 1–Supélec, avril 2000.
A.R. Baig and R. Séguier and G. Vaucher. A Spatio-Temporal Neural Network applied to Visual Speech Recognition. In Int. Conf. on ANN, pp. 797–802, Sept. 1999.
G.M. Georgiou and C. Koutsougeras. Complex domain backpropagation. IEEE trans. on circuits and systems–II: Analog and digital signal processing, 39(5):330–4, May 1992.
W. Gerstner and W. Kistler. Spiking Neuron Models. Cambridge Univ. Press, 2002.
A. Hirose. Continuous complex-valued back-propagation learning. Electronics Letters, 20(20):1854–5, Sept 1992.
D. Mercier. Hétéro-association de signaux audio-vidéo par réseaux de neurones. PhD thesis, Univ. Rennes 1–Supélec, 2003.
D. Mercier and R. Séguier. Un prétraitement simplifié pour les STANN–Illustration en lecture labiale. In Journées Neurosciences et Sciences de l’Ingénieur. Sept 2000.
D. Mercier and R. Séguier. Spiking neurons (STANNs) in Speech Recognition. In 3rd WSEAS Int. Conf. on Neural Networks and Applications, Feb 2002.
J.R. Movellan. Visual Speech Recognition with Stochastic Networks. vol. 7, pp. 851–8. MIT Press, Cambridge. 1995. In Advances in Neural Information Processing Systems. G. Tesauro, D.S. Touretzky and T. Leen (eds).
N. Mozayyani. Introduction d’un codage spatio-temporel dans les architectures classiques de réseaux de neurones artificiels. PhD thesis, Univ. Rennes 1–Supélec, Juil. 1998.
N. Mozayyani and V. Alanou and J.-F. Dreyfus and G. Vaucher. A spatio-temporal data-coding applied to Kohonen maps. In Int. Conf. on ANN, vol. 2, pp. 75–79.E C2 et Compagnie, Oct. 1995.
N. Mozayyani and A.R. Baig and G. Vaucher. A Fully-Neural Solution for on-Line Handwritten Character Recognition. IEEE Int. Joint Conf. on Neural Networks, pp. 160–4, May 1998, Alaska.
N. Mozayyani and G. Vaucher. A spatio-temporal perceptron for on-line handwritten character recognition. In Springer, editor, Int. Conf. ANN, pp. 325–30, Oct 1997.
W. Rall and H. Agmon-Snir. Cable Theory for Dendritic Neurons, in Methods in Neuronal Modeling, chap. 2, pp. 27–92. MIT Press, 1998. C. Koch and I. Segev (eds).
R. Séguier and D. Mercier. Audio-Visual Speech Recognition, One Pass Learning with Spiking Neurons. In Int. Conf. on ANN, Aug 2002.
G. Vaucher. A la recherche d’une algébre neuronale spatio-temporelle. PhD thesis, Univ. Rennes 1–Supélec, Déc 1996.
G. Vaucher. An algebra for recognition of spatio-temporal forms. In D facto publications, editor, European Symp. on ANN, pp. 231–6, April 1997.
G. Vaucher. An algebraic interpretation of PSP composition. BioSystems, 48(1–3):241–6, Sept–Dec 1998.
G. Vaucher and A.R. Baig and R. Séguier. A Set of Neural Tools for Human-Computer Interactions: Application to the Handwritten Character Recognition, and Visual Speech Recognitions Problems. Neural Computing & Applications,9:297–305, dec 2000.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Vaucher, G. (2003). A Complex-Valued Spiking Machine. In: Kaynak, O., Alpaydin, E., Oja, E., Xu, L. (eds) Artificial Neural Networks and Neural Information Processing — ICANN/ICONIP 2003. ICANN ICONIP 2003 2003. Lecture Notes in Computer Science, vol 2714. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44989-2_115
Download citation
DOI: https://doi.org/10.1007/3-540-44989-2_115
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40408-8
Online ISBN: 978-3-540-44989-8
eBook Packages: Springer Book Archive