Abstract
This paper introduces a way to learn cross-modal convolutional neural network (X-CNN) architectures from a base convolutional network (CNN) and the training data to reduce the design cost and enable applying cross-modal networks in sparse data environments. Two approaches for building X-CNNs are presented. The base approach learns the topology in a data-driven manner, by using measurements performed on the base CNN and supplied data. The iterative approach performs further optimisation of the topology through a combined learning procedure, simultaneously learning the topology and training the network. The approaches were evaluated agains examples of hand-designed X-CNNs and their base variants, showing superior performance and, in some cases, gaining an additional 9% of accuracy. From further considerations, we conclude that the presented methodology takes less time than any manual approach would, whilst also significantly reducing the design complexity. The application of the methods is fully automated and implemented in Xsertion library (Code is publicly available at https://github.com/karazijal/xsertion).
Keywords
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
A linear classifier is trained using outputs of frozen intermediate layers as inputs, measuring generalisation performance.
- 2.
For example, it is known that nearly always the initial convolutional layers in CNNs learn to be edge extractors [22].
- 3.
This should not be confused with parameters of the layers themselves, in other literature sometimes referred to as weights as well.
References
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A.A., Veness, J., Bellemare, M.G., Graves, A., Riedmiller, M., Fidjeland, A.K., Ostrovski, G., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015)
Hinton, G., Deng, L., Yu, D., Dahl, G.E., Mohamed, A.R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T.N., et al.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Sig. Process. Mag. 29(6), 82–97 (2012)
Veličković, P., Wang, D., Laney, N.D., Liò, P.: X-CNN: cross-modal convolutional neural networks for sparse datasets. In: 2016 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 1–8. IEEE (2016)
Velickovic, P., Karazija, L., Lane, N.D., Bhattacharya, S., Liberis, E., Lio, P., Chieh, A., Bellahsen, O., Vegreville, M.: Cross-modal recurrent models for weight objective prediction from multimodal time-series data. arXiv e-prints (2017)
Yao, X.: Evolving artificial neural networks. Proc. IEEE 87(9), 1423–1447 (1999)
Yao, X., Liu, Y.: EPNet for chaotic time-series prediction. In: Yao, X., Kim, J.-H., Furuhashi, T. (eds.) SEAL 1996. LNCS, vol. 1285, pp. 146–156. Springer, Heidelberg (1997). https://doi.org/10.1007/BFb0028531
Stanley, K.O., Bryant, B.D., Miikkulainen, R.: Real-time neuroevolution in the nero video game. IEEE Trans. Evol. Comput. 9(6), 653–668 (2005)
Zhang, B.T., Ohm, P., Mühlenbein, H.: Evolutionary induction of sparse neural trees. Evol. Comput. 5(2), 213–236 (1997)
Chen, Y., Yang, B., Dong, J., Abraham, A.: Time-series forecasting using flexible neural tree model. Inf. Sci. 174(3), 219–235 (2005)
Molchanov, P., Tyree, S., Karras, T., Aila, T., Kautz, J.: Pruning convolutional neural networks for resource efficient transfer learning. CoRR abs/1611.06440 (2016)
Hu, H., Peng, R., Tai, Y., Tang, C.: Network trimming: a data-driven neuron pruning approach towards efficient deep architectures. CoRR abs/1607.03250 (2016)
Wen, W., Wu, C., Wang, Y., Chen, Y., Li, H.: Learning structured sparsity in deep neural networks. In: Advances in Neural Information Processing Systems, pp. 2074–2082 (2016)
Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition. CoRR abs/1707.07012 (2017)
Real, E., Moore, S., Selle, A., Saxena, S., Suematsu, Y.L., Le, Q.V., Kurakin, A.: Large-scale evolution of image classifiers. CoRR abs/1703.01041 (2017)
Baker, B., Gupta, O., Naik, N., Raskar, R.: Designing neural network architectures using reinforcement learning. CoRR abs/1611.02167 (2016)
Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: FitNets: hints for thin deep nets. CoRR abs/1412.6550 (2014)
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 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)
Srivastava, R.K., Greff, K., Schmidhuber, J.: Highway networks. CoRR abs/1505.00387 (2015)
Alain, G., Bengio, Y.: Understanding intermediate layers using linear classifier probes. arXiv preprint arXiv:1610.01644 (2016)
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818–833. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10590-1_53
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. CoRR abs/1412.6980 (2014)
Dozat, T.: Incorporating nesterov momentum into adam (2016). http://cs229.stanford.edu/proj2015/054_report.pdf
Chollet, F., et al.: Train a simple deep CNN on the CIFAR10 small images dataset (2015). https://github.com/keras-team/keras/blob/master/examples/cifar10_cnn.py
Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images (2009). https://www.cs.toronto.edu/~kriz/learning-features-2009-TR.pdf
Targ, S., Almeida, D., Lyman, K.: Resnet in resnet: Generalizing residual architectures. CoRR abs/1603.08029 (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)
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
Karazija, L., Veličković, P., Liò, P. (2018). Automatic Inference of Cross-Modal Connection Topologies for X-CNNs. 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_7
Download citation
DOI: https://doi.org/10.1007/978-3-319-92537-0_7
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)