Abstract
Recently, deep neural networks have showed amazing results in many fields. To build such networks, we usually use layers from a relatively small dictionary of available modules (fully-connected, convolutional, recurrent, etc.). Being restricted with this set of modules complicates transferring technology to new tasks. On the other hand, many important applications already have a long history and successful algorithmic solutions. Is it possible to use existing methods to construct better networks? In this paper, we cover three approaches to combining neural networks with algorithms and discuss their pros and cons. Specifically, we will discuss three approaches: structured pooling, unrolling of algorithm iterations into network layers and explicit differentiation of the output w.r.t. the input.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abadi, M., Agarwal, A., Barham, P., et al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). http://tensorflow.org/
Agrawal, A., Amos, B., Barratt, S., Boyd, S., Diamond, S., Kolter, Z.: Differentiable convex optimization layers. In: Advances in Neural Information Processing Systems 32 (NeuIPS) (2019)
Andrychowicz, M., et al.: Learning to learn by gradient descent by gradient descent. In: Advances in Neural Information Processing Systems 29 (NIPS) (2016)
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: Proceedings of the International Conference on Learning Representations (ICLR) (2015)
Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, New York (2006). https://www.microsoft.com/en-us/research/people/cmbishop/#!prml-book
Borenstein, E., Ullman, S.: Class-specific, top-down segmentation. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2351, pp. 109–122. Springer, Heidelberg (2002). https://doi.org/10.1007/3-540-47967-8_8
Bottou, L., Le Cun, Y., Bengio, Y.: Global training of document processing systems using graph transformer networks. In: Proceedings of Conference on Computer Vision and Pattern Recognition (CVPR) (1997)
Chandra, S., Kokkinos, I.: Fast, exact and multi-scale inference for semantic image segmentation with deep Gaussian CRFs. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 402–418. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46478-7_25
Chandra, S., Usunier, N., Kokkinos, I.: Dense and low-rank Gaussian CRFs using deep embeddings. In: Proceedings of International Conference on Computer Vision (ICCV) (2017)
Chen, L., Schwing, A., Yuille, A., Urtasun, R.: Learning deep structured models. In: Proceedings of the International Conference on Machine Learning (ICML) (2015)
Chen, T.Q., Rubanova, Y., Bettencourt, J., Duvenaud, D.K.: Neural ordinary differential equations. In: Advances in Neural Information Processing Systems 31 (NeuIPS) (2018)
Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K., Kuksa, P.: Natural language processing (almost) from scratch. J. Mach. Learn. Res. 12, 2493–2537 (2011)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding (2018). arXiv:1810.04805
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 580–587 (2014)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016). http://www.deeplearningbook.org
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 (CVPR) (2016)
Hinton, G., et al.: Deep neural networks for acoustic modeling in speech recognition. IEEE Sig. Process. Mag. 29, 82–97 (2012)
Ionescu, C., Vantzos, O., Sminchisescu, C.: Matrix backpropagation for deep networks with structured layers. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2015)
Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Deep structured output learning for unconstrained text recognition (2014). arXiv:1412.5903v5
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems 25 (NeuIPS) (2012)
Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of the International Conference on Machine Learning (ICML) (2001)
Le Cun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Leblond, R., Alayrac, J.B., Osokin, A., Lacoste-Julien, S.: SEARNN: training RNNs with global-local losses. In: Proceedings of International Conference on Learning Representations (ICLR) (2018)
LeCun, Y., Chopra, S., Hadsell, R., Ranzato, M., Huang, F.J.: Energy-based models. In: Bakir, G.H., Hofmann, T., Schölkopf, B., Smola, A.J., Taskar, B., Vishwanathan, S.V.N. (eds.) Predicting Structured Data (2006)
Lefkimmiatis, S.: Non-local color image denoising with convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)
Maclaurin, D., Duvenaud, D., Adams, R.: Gradient-based hyperparameter optimization through reversible learning. In: Proceedings of the International Conference on Machine Learning (ICML) (2015)
Metz, L., Poole, B., Pfau, D., Sohl-Dickstein, J.: Unrolled generative adversarial networks. In: Proceedings of the International Conference on Learning Representations (ICLR) (2017)
Osokin, A.: How to put algorithms into neural networks. In: CEUR Workshop Proceedings: Proceedings of the International Conference on Data Analytics and Management in Data Intensive Domains (DAMDID/RCDL) (2019)
Paszke, A., Gross, S., Massa, F., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems 32 (NeuIPS) (2019)
Pérez-Cruz, F., Ghahramani, Z., Pontil, M.: Conditional graphical models. In: Bakir, G.H., Hofmann, T., Schölkopf, B., Smola, A.J., Taskar, B., Vishwanathan, S.V.N. (eds.) Predicting Structured Data. MIT Press, Cambridge (2007)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 39(6), 1137–1149 (2017)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention (2015)
Shevchenko, A., Osokin, A.: Scaling matters in deep structured-prediction models (2019). arXiv:1902.11088
Taskar, B., Guestrin, C., Koller, D.: Max-margin Markov networks. In: Proceedings of Neural Information Processing Systems Conference (NIPS) (2003)
Tsochantaridis, I., Joachims, T., Hofmann, T., Altun, Y.: Large margin methods for structured and interdependent output variables. J. Mach. Learn. Res. 6, 1453–1484 (2005)
van den Oord, A., Li, Y., Babuschkin, I., Simonyan, K., et al.: Parallel WaveNet: fast high-fidelity speech synthesis. In: Proceedings of the International Conference on Machine Learning (ICML) (2018)
Vu, T., Osokin, A., Laptev, I.: Context-aware CNNs for person head detection. In: Proceedings of International Conference on Computer Vision (ICCV) (2015)
Wu, Y., et al.: Google’s neural machine translation system: bridging the gap between human and machine translation (2016). arXiv:1609.08144
Zheng, S., et al.: Conditional random fields as recurrent neural networks. In: Proceedings of International Conference on Computer Vision (ICCV) (2015)
Acknowledgements
This work was supported by the Russian Science Foundation project 19-71-00082.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Osokin, A. (2020). Three Simple Approaches to Combining Neural Networks with Algorithms. In: Elizarov, A., Novikov, B., Stupnikov, S. (eds) Data Analytics and Management in Data Intensive Domains. DAMDID/RCDL 2019. Communications in Computer and Information Science, vol 1223. Springer, Cham. https://doi.org/10.1007/978-3-030-51913-1_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-51913-1_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-51912-4
Online ISBN: 978-3-030-51913-1
eBook Packages: Computer ScienceComputer Science (R0)