Skip to main content

2020 | OriginalPaper | Buchkapitel

DartsReNet: Exploring New RNN Cells in ReNet Architectures

verfasst von : Brian B. Moser, Federico Raue, Jörn Hees, Andreas Dengel

Erschienen in: Artificial Neural Networks and Machine Learning – ICANN 2020

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

We present new Recurrent Neural Network (RNN) cells for image classification using a Neural Architecture Search (NAS) approach called DARTS. We are interested in the ReNet architecture, which is a RNN based approach presented as an alternative for convolutional and pooling steps. ReNet can be defined using any standard RNN cells, such as LSTM and GRU. One limitation is that standard RNN cells were designed for one dimensional sequential data and not for two dimensions like it is the case for image classification. We overcome this limitation by using DARTS to find new cell designs. We compare our results with ReNet that uses GRU and LSTM cells. Our found cells outperform the standard RNN cells on CIFAR-10 and SVHN. The improvements on SVHN indicate generalizability, as we derived the RNN cell designs from CIFAR-10 without performing a new cell search for SVHN. (The source code of our approach and experiments is available at https://​github.​com/​LuckyOwl95/​DartsReNet/​.).

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Baker, B., Gupta, O., Naik, N., Raskar, R.: Designing neural network architectures using reinforcement learning. arXiv preprint arXiv:1611.02167 (2016) Baker, B., Gupta, O., Naik, N., Raskar, R.: Designing neural network architectures using reinforcement learning. arXiv preprint arXiv:​1611.​02167 (2016)
2.
Zurück zum Zitat Breuel, T.M., Ul-Hasan, A., Al-Azawi, M.A., Shafait, F.: High-performance OCR for printed English and fraktur using LSTM networks. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 683–687. IEEE (2013) Breuel, T.M., Ul-Hasan, A., Al-Azawi, M.A., Shafait, F.: High-performance OCR for printed English and fraktur using LSTM networks. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 683–687. IEEE (2013)
4.
Zurück zum Zitat Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014) Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:​1406.​1078 (2014)
5.
Zurück zum Zitat Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR09 (2009) Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR09 (2009)
6.
Zurück zum Zitat DeVries, T., Taylor, G.W.: Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552 (2017) DeVries, T., Taylor, G.W.: Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:​1708.​04552 (2017)
7.
Zurück zum Zitat Graves, A., Schmidhuber, J.: Offline handwriting recognition with multidimensional recurrent neural networks. In: Advances in Neural Information Processing Systems, pp. 545–552 (2009) Graves, A., Schmidhuber, J.: Offline handwriting recognition with multidimensional recurrent neural networks. In: Advances in Neural Information Processing Systems, pp. 545–552 (2009)
8.
Zurück zum Zitat 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.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
9.
Zurück zum Zitat Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRef Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRef
10.
Zurück zum Zitat Krizhevsky, A., Hinton, G., et al.: Learning Multiple Layers of Features from Tiny Images (2009) Krizhevsky, A., Hinton, G., et al.: Learning Multiple Layers of Features from Tiny Images (2009)
13.
Zurück zum Zitat Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading Digits in Natural Images with Unsupervised Feature Learning (2011) Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading Digits in Natural Images with Unsupervised Feature Learning (2011)
14.
Zurück zum Zitat Pham, H., Guan, M.Y., Zoph, B., Le, Q.V., Dean, J.: Efficient neural architecture search via parameter sharing. arXiv preprint arXiv:1802.03268 (2018) Pham, H., Guan, M.Y., Zoph, B., Le, Q.V., Dean, J.: Efficient neural architecture search via parameter sharing. arXiv preprint arXiv:​1802.​03268 (2018)
15.
Zurück zum Zitat Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014) Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:​1409.​1556 (2014)
16.
Zurück zum Zitat Stollenga, M.F., Byeon, W., Liwicki, M., Schmidhuber, J.: Parallel multi-dimensional LSTM, with application to fast biomedical volumetric image segmentation. In: Advances in Neural Information Processing Systems, pp. 2998–3006 (2015) Stollenga, M.F., Byeon, W., Liwicki, M., Schmidhuber, J.: Parallel multi-dimensional LSTM, with application to fast biomedical volumetric image segmentation. In: Advances in Neural Information Processing Systems, pp. 2998–3006 (2015)
17.
Zurück zum Zitat Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015) Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)
18.
Zurück zum Zitat Visin, F., Kastner, K., Cho, K., Matteucci, M., Courville, A., Bengio, Y.: Renet: a recurrent neural network based alternative to convolutional networks. arXiv preprint arXiv:1505.00393 (2015) Visin, F., Kastner, K., Cho, K., Matteucci, M., Courville, A., Bengio, Y.: Renet: a recurrent neural network based alternative to convolutional networks. arXiv preprint arXiv:​1505.​00393 (2015)
Metadaten
Titel
DartsReNet: Exploring New RNN Cells in ReNet Architectures
verfasst von
Brian B. Moser
Federico Raue
Jörn Hees
Andreas Dengel
Copyright-Jahr
2020
DOI
https://doi.org/10.1007/978-3-030-61609-0_67