Abstract
This work presents a new type of Spike Neural Networks (SNN) developed in the quaternion algebra framework. This new neural structure based on SNN is developed using the quaternion algebra. The training algorithm was extended adjusting the weights according to the quaternion multiplication rule, which allows accurate results with a decreased network complexity with respect to the real SNN. The experimental part shows a good performance for robot manipulator control.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wolfgang, M.: Networks of spiking neurons: the third generation of neural network models. IEEE Trans. Neural Netw. 9, 1659–1671 (1997)
Haykin, S.: Neural Networks: A Comprehensive Foundation. Prentice-Hall, New York (1999)
Wulfram, G., Werner, M.: Spiking Neuron Models, Single Neurons, Population, Plasticity. MIT Press, Cambridge (2002)
Van Rullen, R., Delorme, A., Gautrais, J., Thorpe, S.: (SpikeNET): a simulator for modeling large networks of integrate and fire neurons. Neurocomput. 22, 989–996 (1999)
Bohte, S., Kok, J., Han, L.: Error-backpropagation in temporally encoded networks of spiking neurons. Neurocomput. 48, 17–37 (2002)
Eduardo, B.C.: TGeometric Computing, for Wavelets Transforms, Robot Vision, Learning, Control and Action. Springer, London (2010)
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
Lechuga-Gutiérrez, L., Bayro-Corrochano, E. (2016). Quaternion Spike Neural Networks. 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_73
Download citation
DOI: https://doi.org/10.1007/978-3-319-40663-3_73
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)