Abstract
Capsule network is a new neural network architecture, which avoids the problem of location information loss due to the pool operation of the convolution neural network. The capsule network uses vector as input and output and dynamic routing updates parameters, which has better effect than convolution neural network. In this paper, a new activation function is proposed for the capsule network and the least weight loss is added to the loss function. The experiment shows that the improved capsule network improves the convergence speed of the network, increases the generalization ability, and makes the network more efficient.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhang, P., Ma, X.H., Ding, S.X.: Audio source separation from a monaural mixture using convolutional neural network in the time domain. In: Cong, F., Leung, A., Wei, Q. (eds.) ISNN 2017. LNCS, vol. 10262, pp. 388–395. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-59081-3_46
Jia, S., Liu, H., Sun, F.: Aerial scene classification with convolutional neural networks. In: Hu, X., Xia, Y., Zhang, Y., Zhao, D. (eds.) ISNN 2015. LNCS, vol. 9377, pp. 258–265. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-25393-0_29
Kim, Y.: Convolutional Neural Networks for Sentence Classification. University of Waterloo (2015)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: 26th Annual Conference on Neural Information Processing Systems (NIPS), pp. 1097–1105 (2012)
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1–9 (2015)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv (2014)
He, K.M., Zhang, X.Y., Ren, S.Q., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)
Huang, G., Liu, Z., Weinberger, K.Q., Maaten, L.: Densely connected convolutional networks. arXiv (2016)
Sabour, S., Frosst, N., Hinton, G.: Dynamic routing between capsules. In: Advances in Neural Information Processing Systems (NIPS), pp. 3859–3869 (2017)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv (2014)
Acknowledgements
This work was supported by the National Natural Science Foundation of China under Grant 61571372, 61672436, 61372139 and 61601376, the Natural Science Foundation of Chongqing under Grant cstc2017jcyjBX0050, and the Fundamental Research Funds for the Central Universities under Grant XDJK2017A005 and XDJK2016A001.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Zou, X., Duan, S., Wang, L., Zhang, J. (2018). Fast Convergent Capsule Network with Applications in MNIST. In: Huang, T., Lv, J., Sun, C., Tuzikov, A. (eds) Advances in Neural Networks – ISNN 2018. ISNN 2018. Lecture Notes in Computer Science(), vol 10878. Springer, Cham. https://doi.org/10.1007/978-3-319-92537-0_1
Download citation
DOI: https://doi.org/10.1007/978-3-319-92537-0_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-92536-3
Online ISBN: 978-3-319-92537-0
eBook Packages: Computer ScienceComputer Science (R0)