Abstract
A fast two-stage learning algorithm is proposed to construct and optimize the weights of spline activation function neural networks (SAFNN). Feedforward network is firstly trained by back propagate (BP) algorithm, and then errors are applied to generate new neurons in hidden layers. A rapid dynamic updating algorithm is introduced to modify the new weights. Generalization capability and approximation precision are ensured by the two steps respectively. Simulation results on biped gaits demonstrate improvements in these two capabilities and of learning speed with comparison to traditional BP in SFANN and common NN.
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
McCulloch, W.S., Pitts, W.: A Logical Calculus of the Ideas Imminent in Nervous Activity. Bull. Math. Biophys. 5, 115–133 (1943)
Chen, C.T., Chang, W.D.: A Feedforward Neural Network with Function Shape Auto Tuning. Neural Networks 9, 627–641 (1996)
Piazza, F., Uncini, A., Zenobi, M.: Neural Networks with Digital LUT Activation Function. In: Proc. of the IJCNN, Beijing, China, vol. 2, pp. 343–349 (1993)
Vecci, L. (ed.): Learning and Approximation Capabilities of Adaptive Spline Activation Function Neural Networks. Neural Networks 11, 259–270 (1998)
Guarnieri, S. (ed.): Multilayer Feedforward Networks with Adaptive Spline Activation Function. IEEE Tran. Neural Networks 10(3), 672–683 (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hu, L., Sun, Z. (2004). A Rapid Two-Step Learning Algorithm for Spline Activation Function Neural Networks with the Application on Biped Gait Recognition. In: Yin, FL., Wang, J., Guo, C. (eds) Advances in Neural Networks – ISNN 2004. ISNN 2004. Lecture Notes in Computer Science, vol 3173. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-28647-9_49
Download citation
DOI: https://doi.org/10.1007/978-3-540-28647-9_49
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22841-7
Online ISBN: 978-3-540-28647-9
eBook Packages: Springer Book Archive