Abstract
A novel feed forward Neural Network architecture is proposed based on Shepard Interpolation. Shepard Interpolation is a method for approximating multi-dimensional functions with known coordinate-value pairs [4]. In a Shepard Interpolation Neural Network (SINN), weights and biases are deterministically initiated to non-zero values. Furthermore, Shepard networks maintain a similar accuracy as traditional Neural Networks with a reduction in memory footprint and number of hyper parameters such as number of layers, layer sizes and activation functions. Shepard Interpolation Networks greatly reduce the complexity of Neural Networks, improving performance while maintaining accuracy. The accuracy of Shepard Networks is evaluated on the MNIST digit recognition task. The proposed architecture is compared to LeCun et al. original work on Neural networks [9].
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Haykin, S.: Neural networks: a comprehensive foundation. Neural Netw. 2(2004) (2004)
Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural networks 2(5), 359–366 (1989)
Ren, J.S.J., et al.: Shepard convolutional neural networks. In: Advances in Neural Information Processing Systems (2015)
Shepard, D.: A two-dimensional interpolation function for irregularly-spaced data. In: Proceedings of the 1968 23rd ACM National Conference. ACM (1968)
“Metric (mathematics)”: Wikipedia: The Free Encyclopedia. Wikimedia Foundation, Inc., Web Date accessed 10 August 2016. https://en.wikipedia.org/wiki/Metric_(mathematics). Date last updated (21 August 2016)
Gordon, W.J., Wixom, J.A.: Shepard’s method of “metric interpolation” to bivariate and multivariate interpolation. Math. Comput. 32(141), 253–264 (1978)
Nielsen, M.A.: Neural Networks and Deep Learning. Determination Press (2015)
LeCun, Y., et al.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Singer, S., Nelder, J.: Nelder-Mead algorithm. Scholarpedia 4(7), 2928 (2009)
Glorot, X., Antoine, B., Yoshua, B.: Deep sparse rectifier neural networks. Aistats 15(106), 275 (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Williams, P. (2016). SINN: Shepard Interpolation Neural Networks. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2016. Lecture Notes in Computer Science(), vol 10073. Springer, Cham. https://doi.org/10.1007/978-3-319-50832-0_34
Download citation
DOI: https://doi.org/10.1007/978-3-319-50832-0_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-50831-3
Online ISBN: 978-3-319-50832-0
eBook Packages: Computer ScienceComputer Science (R0)