Deep neural networks; residual learning; optimization
Abstract :
[en] Many works have posited the benefit of depth in deep networks. However,
one of the problems encountered in the training of very deep networks is feature
reuse; that is, features are ’diluted’ as they are forward propagated through
the model. Hence, later network layers receive less informative signals about the
input data, consequently making training less effective. In this work, we address
the problem of feature reuse by taking inspiration from an earlier work which
employed residual learning for alleviating the problem of feature reuse. We propose
a modification of residual learning for training very deep networks to realize
improved generalization performance; for this, we allow stochastic shortcut connections
of identity mappings from the input to hidden layers.We perform extensive
experiments using the USPS and MNIST datasets. On the USPS dataset, we
achieve an error rate of 2.69% without employing any form of data augmentation
(or manipulation). On the MNIST dataset, we reach a comparable state-of-the-art
error rate of 0.52%. Particularly, these results are achieved without employing
any explicit regularization technique.
Research center :
Interdisciplinary Centre for Security, Reliability and Trust (SnT) > SIGCOM
Disciplines :
Computer science
Author, co-author :
Oyedotun, Oyebade ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Shabayek, Abd El Rahman ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Aouada, Djamila ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Ottersten, Björn ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
External co-authors :
yes
Language :
English
Title :
Training Very Deep Networks via Residual Learning with Stochastic Input Shortcut Connections
Publication date :
31 July 2017
Event name :
24th International Conference on Neural Information Processing, Guangzhou, China, November 14–18, 2017
Event place :
Guangzhou, China
Event date :
November 14–18, 2017
Audience :
International
Main work title :
24th International Conference on Neural Information Processing, Guangzhou, China, November 14–18, 2017
Funahashi, K.I.: On the approximate realization of continuous mappings by neural networks. Neural Netw. 2(3), 183–192 (1989)
Delalleau, O., Bengio, Y.: Shallow vs. deep sum-product networks. In: Advances in Neural Information Processing Systems, pp. 666–674 (2011)
Mhaskar, H., Liao, Q., Poggio, T.: Learning functions: When is deep better than shallow. arXiv preprint (2016). arXiv:1603.00988
Bianchini, M., Scarselli, F.: On the complexity of neural network classifiers: a comparison between shallow and deep architectures. IEEE Trans. Neural Netw. Learn. Syst. 25(8), 1553–1565 (2014)
Wan, L., Zeiler, M., Zhang, S., Cun, Y.L., Fergus, R.: Regularization of neural networks using dropconnect. In: Proceedings of the 30th International Conference on Machine Learning (ICML-2013), pp. 1058–1066 (2013)
Clevert, D.A., Unterthiner, T., Hochreiter, S.: Fast and accurate deep network learning by exponential linear units (ELUs), arXiv preprint, arXiv:1511.07289 (2015)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition, arXiv preprint, arXiv:1409.1556 (2014)
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)
Srivastava, R.K., Greff, K., Schmidhuber, J.: Training very deep networks. In: Advances in Neural Information Processing Systems, pp. 2377–2385 (2015)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
He, K., Zhang, X., Ren, S., Sun, J.: 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)
Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. AISTATS 9, 249–256 (2010)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift, arXiv preprint, arXiv:1502.03167 (2015)
He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: European Conference on Computer Vision, pp. 630–645 (2016)
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
Schlkopf, B., Simard, P., Smola, A., Vapnik, V.: Prior knowledge in support vector Kernels. In: Proceedings of the 10th International Conference on Neural Information Processing Systems, pp. 640–646 (1997)
Simard, P.Y., LeCun, Y.A., Denker, J.S., Victorri, B.: Transformation invariance in pattern recognition – tangent distance and tangent propagation. In: Montavon, G., Orr, G.B., Müller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 7700, pp. 235–269. Springer, Heidelberg (2012). doi:10.1007/978-3-642-35289-8_17
Wu, M., Schlkopf, B., Bakir, G.: Building sparse large margin classifiers. In: Proceedings of the 22nd International Conference on Machine Learning, pp. 996–1003 (2005)
Simard, P., LeCun, Y., Denker, J.S.: Efficient pattern recognition using a new transformation distance. In: Advances in Neural Information Processing Systems, pp. 50–58 (1993)
Keysers, D., Dahmen, J., Theiner, T., Ney, H.: Experiments with an extended tangent distance. In: 15th International Conference on Pattern Recognition, Proceedings, vol. 2, pp. 38–42 (2000)
Yang, J., Yu, K., Huang, T.: Supervised translation-invariant sparse coding. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3517– 3524 (2010)
Yang, Z., Moczulski, M., Denil, M., de Freitas, N., Smola, A., Song, L., Wang, Z.: Deep fried convnets. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1476–1483 (2015)
Chan, T.H., Jia, K., Gao, S., Lu, J., Zeng, Z., Ma, Y.: Pcanet: a simple deep learning baseline for image classification? IEEE Trans. Image Process. 24(12), 5017–5032 (2015)
Lin, M., Chen, Q., Yan, S.: Network in network. In: International Conference on Learning Representations, abs/1312.4400 (2014)
Lee, C.Y., Xie, S., Gallagher, P., Zhang, Z., Tu, Z.: Deeply-supervised nets. In: Artificial Intelligence and Statistics, pp. 562–570 (2015)
Ngiam, J., Coates, A., Lahiri, A., Prochnow, B., Le, Q.V., Ng, A.Y.: On optimization methods for deep learning. In: Proceedings of the 28th International Conference on Machine Learning (ICML-2011), pp. 265–272 (2011)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: International Conference on Learning Representations, arXiv preprint, arXiv:1412.6572 (2015)
Huang, G., Sun, Y., Liu, Z., Sedra, D., Weinberger, K.Q.: Deep networks with stochastic depth. In: European Conference on Computer Vision, pp. 646–661 (2016)