Abstract
Model combination nearly always improves the performance of machine learning methods. Averaging the predictions of multi-model further decreases the error rate. In order to obtain multi high quality models more quickly, this article proposes a novel deep network architecture called “Fissionable Deep Neural Network”, abbreviated as FDNN. Instead of just adjusting the weights in a fixed topology network, FDNN contains multi branches with shared parameters and multi Softmax layers. During training, the model divides until to be multi models. FDNN not only can reduce computational cost, but also overcome the interference of convergence between branches and give an opportunity for the branches falling into a poor local optimal solution to re-learn. It improves the performance of neural network on supervised learning which is demonstrated on MNIST and CIFAR-10 datasets.
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
Srivastava, N., Hinton, G., Krizhevsky, A., et al.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
Ciresan, D., Meier, U., Schmidhuber, J.: Multi-column deep neural networks for image classification. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3642–3649. IEEE (2012)
Elman, J.L.: Learning and development in neural networks: the importance of starting small. Cognition 48(1), 71–99 (1993)
Mishkin, D., Matas, J.: All you need is a good init (2015). arXiv preprint arXiv:1511.06422
Szegedy, C., Liu, W., Jia, Y., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift (2015). arXiv preprint arXiv:1502.03167
Szegedy, C., Vanhoucke, V., Ioffe, S., et al.: Rethinking the Inception Architecture for Computer Vision (2015). arXiv preprint arXiv:1512.00567
Szegedy, C., Ioffe, S., Vanhoucke, V.: Inception-v4, inception-resnet and the impact of residual connections on learning (2016). arXiv preprint arXiv:1602.07261
Springenberg, J.T., Dosovitskiy, A., Brox, T., et al.: Striving for simplicity: The all convolutional net (2014). arXiv preprint arXiv:1412.6806
He, K., Zhang, X., Ren, S., et al.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1026–1034 (2015)
Maas, A.L., Hannun, A.Y., Ng, A.Y.: Rectifier nonlinearities improve neural network acoustic models. In: Proceedings of ICML, vol. 30, no. 1 (2013)
Goodfellow, I.J., Warde-Farley, D., Mirza, M., et al.: Maxout networks (2013). arXiv preprint arXiv:1302.4389
Fahlman, S.E., Lebiere, C.: The cascade-correlation learning architecture (1989)
LeCun, Y., Denker, J.S., Solla, S.A., et al.: Optimal brain damage. In: NIPs (1989)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Master’s thesis, Department of Computer Science, University of Toronto (2009)
Lin, M., Chen, Q., Yan, S.: Network in network (2013). CoRR, abs/1312.4400
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
Tan, D., Wu, J., Zheng, H., Yin, Y., Liu, Y. (2016). Fissionable Deep Neural Network. In: Hirose, A., Ozawa, S., Doya, K., Ikeda, K., Lee, M., Liu, D. (eds) Neural Information Processing. ICONIP 2016. Lecture Notes in Computer Science(), vol 9950. Springer, Cham. https://doi.org/10.1007/978-3-319-46681-1_44
Download citation
DOI: https://doi.org/10.1007/978-3-319-46681-1_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-46680-4
Online ISBN: 978-3-319-46681-1
eBook Packages: Computer ScienceComputer Science (R0)