Skip to main content

2020 | OriginalPaper | Buchkapitel

Orthogonalizing Weights in Capsule Network Architecture

verfasst von : Shubhranil Kundu, B. Gagana

Erschienen in: ICT Analysis and Applications

Verlag: Springer Singapore

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

search-config
loading …

Abstract

Scalar neural network algorithms are limited in their ability to understand scale, rotational, or affine transformations within images and resort to average or max-pooling techniques which result in translational invariance. In an attempt to overcome these limitations, Hinton et al. introduced vectorized capsule network frameworks which support equivariance while capturing spatial relationships between data points, thus enhancing predictive capabilities of networks. However, experimenting with activation functions, hyperparameters, and optimizers have proven faster convergence and orthogonalizing weights within the layers of capsules enhance performance by slashing associated average error rates.

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 Sabour S, Frosst N, Hinton G (2017) Dynamic routing between capsules. In: Thirty first conference on neural information processing systems. arXiv:1710.09829 Sabour S, Frosst N, Hinton G (2017) Dynamic routing between capsules. In: Thirty first conference on neural information processing systems. arXiv:​1710.​09829
2.
Zurück zum Zitat Hinton G, Sabour S, Frosst N (2018) Matrix capsules with EM routing. In: International conference on learning representations Hinton G, Sabour S, Frosst N (2018) Matrix capsules with EM routing. In: International conference on learning representations
3.
Zurück zum Zitat Pascanu R, Mikolov T, Bengio Y (2013) On the difficulty of training recurrent neural networks. In: International conference on machine learning, pp 1310–1318 Pascanu R, Mikolov T, Bengio Y (2013) On the difficulty of training recurrent neural networks. In: International conference on machine learning, pp 1310–1318
4.
Zurück zum Zitat Dauphin Y et al (2014) Identifying and attacking the saddle point problem in high dimensional non convex optimization. In: Advances in neural information processing systems, pp 2933–2941 Dauphin Y et al (2014) Identifying and attacking the saddle point problem in high dimensional non convex optimization. In: Advances in neural information processing systems, pp 2933–2941
5.
Zurück zum Zitat Ioffe S et al (2015) Batch normalization: accelerating deep network training by reducing internal covariance shift. In: International conference on machine learning, pp 448–456 Ioffe S et al (2015) Batch normalization: accelerating deep network training by reducing internal covariance shift. In: International conference on machine learning, pp 448–456
6.
Zurück zum Zitat Bansal N, et al (2018) Can we gain more from orthogonality regularizations in training Deep CNN’s? In: Advances in neural information processing systems. arXiv:1810.09102 Bansal N, et al (2018) Can we gain more from orthogonality regularizations in training Deep CNN’s? In: Advances in neural information processing systems. arXiv:​1810.​09102
8.
Zurück zum Zitat Zhu Z et al (2019) A convolutional neural network based on a capsule network with strong generalisation for bearing fault diagnosis. Neurocomputing 323: 62–75 Zhu Z et al (2019) A convolutional neural network based on a capsule network with strong generalisation for bearing fault diagnosis. Neurocomputing 323: 62–75
9.
10.
Zurück zum Zitat Zhong C (2019) Residual capsule networks. In: 11th annual undergraduate research symposium. Poster session. University of Wisconsin, Milwaukee Zhong C (2019) Residual capsule networks. In: 11th annual undergraduate research symposium. Poster session. University of Wisconsin, Milwaukee
11.
12.
Zurück zum Zitat He S, Shin K (2019) Spatio-temporal capsule based reinforcement learning for mobility-on-demand network coordination. In: Association for computing machinery. ISBN: 978-1-4503-6674-8/19/05 He S, Shin K (2019) Spatio-temporal capsule based reinforcement learning for mobility-on-demand network coordination. In: Association for computing machinery. ISBN: 978-1-4503-6674-8/19/05
13.
Zurück zum Zitat Zhaopeng Xu, Wei Lu, Zhang Qqui, Yeung Yuileong, Chen Xin (2019) Gait recognition based on capsule network. J Vis Commun Image Represent 59:159–167CrossRef Zhaopeng Xu, Wei Lu, Zhang Qqui, Yeung Yuileong, Chen Xin (2019) Gait recognition based on capsule network. J Vis Commun Image Represent 59:159–167CrossRef
14.
Zurück zum Zitat Yao H et al (2019) Capsule network assisted IoT traffic classification mechanism for smart cities. IEEE Internet Things J Yao H et al (2019) Capsule network assisted IoT traffic classification mechanism for smart cities. IEEE Internet Things J
17.
Zurück zum Zitat Qiao K, Zhang C, Wang L, Yan B, Chen J, Zeng L, Tong L (2018) Accurate reconstruction of image stimuli from human fMRI based on the decoding model with capsule network architecture. arXiv:1801.00602 Qiao K, Zhang C, Wang L, Yan B, Chen J, Zeng L, Tong L (2018) Accurate reconstruction of image stimuli from human fMRI based on the decoding model with capsule network architecture. arXiv:​1801.​00602
18.
Zurück zum Zitat Mobiny A, Nguyer H (2018) Fast Capsnet for lung cancer screening. In: Frangi A, Schnabel J, Davatzikos C, Alberola Lopez C, Fichtinger G (eds) Medical image computing and computer assisted intervention (MICCAI). Lecture notes in Computer Science, vol 11071. Springer, Cham Mobiny A, Nguyer H (2018) Fast Capsnet for lung cancer screening. In: Frangi A, Schnabel J, Davatzikos C, Alberola Lopez C, Fichtinger G (eds) Medical image computing and computer assisted intervention (MICCAI). Lecture notes in Computer Science, vol 11071. Springer, Cham
19.
Zurück zum Zitat Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feed forward neural networks. In: Proceedings of thirteenth international conference on artificial intelligence and statistics, pp 249–256 Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feed forward neural networks. In: Proceedings of thirteenth international conference on artificial intelligence and statistics, pp 249–256
20.
Zurück zum Zitat He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: surpassing human-level performance on image classification. In: Proceedings of IEEE international conference on Computer Vision, pp 1026–1034 He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: surpassing human-level performance on image classification. In: Proceedings of IEEE international conference on Computer Vision, pp 1026–1034
21.
Zurück zum Zitat Vorontsov E, Trabelsi C, Kadoury S, Pal C (2017) On orthogonality and learning recurrent networks with long term dependencies. arXiv:1702.00071 Vorontsov E, Trabelsi C, Kadoury S, Pal C (2017) On orthogonality and learning recurrent networks with long term dependencies. arXiv:​1702.​00071
22.
24.
Zurück zum Zitat Xiao H, Rasul K, Vollagraf R (2017) Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. arXiv:1708.07747 Xiao H, Rasul K, Vollagraf R (2017) Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. arXiv:​1708.​07747
25.
Zurück zum Zitat Mass AL et al (2013) Rectified non linearities improve neural network acoustic models. In: International conference on machine learning, vol 30 Mass AL et al (2013) Rectified non linearities improve neural network acoustic models. In: International conference on machine learning, vol 30
26.
Zurück zum Zitat Gagana B, Natarajan S (2019) Hyperparameter optimizations for capsule networks. In: EAI endorsed transactions on cloud systems Gagana B, Natarajan S (2019) Hyperparameter optimizations for capsule networks. In: EAI endorsed transactions on cloud systems
27.
Zurück zum Zitat Gagana B, Athri U, Natarajan S (2018) Activation function optimizations for capsule networks. In: IEEE international conference on advances in computing, communications and informatics. ISBN: 978-1-5386-5314-2 Gagana B, Athri U, Natarajan S (2018) Activation function optimizations for capsule networks. In: IEEE international conference on advances in computing, communications and informatics. ISBN: 978-1-5386-5314-2
28.
Zurück zum Zitat Le QV et al (2017) Swish: a self gated activation function. In: Neural and evolutionary computing, computer vision and pattern recognition. arXiv:1710.05941 Le QV et al (2017) Swish: a self gated activation function. In: Neural and evolutionary computing, computer vision and pattern recognition. arXiv:​1710.​05941
29.
Zurück zum Zitat Liang M et al (2015) Recurrent convolutional neural network for object recognition. In: Conference on computer vision and pattern recognition Liang M et al (2015) Recurrent convolutional neural network for object recognition. In: Conference on computer vision and pattern recognition
31.
Zurück zum Zitat Luo L, Xiong Y, Liu Y, Sun X (2019) Adaptive gradient methods with dynamic bound of learning rate. In: International conference on learning representations Luo L, Xiong Y, Liu Y, Sun X (2019) Adaptive gradient methods with dynamic bound of learning rate. In: International conference on learning representations
32.
Zurück zum Zitat Katebi R (2019) Examining extreme nuclear variability in the galaxies that host Active Galactic Nuclei. American Astronomical Society Katebi R (2019) Examining extreme nuclear variability in the galaxies that host Active Galactic Nuclei. American Astronomical Society
Metadaten
Titel
Orthogonalizing Weights in Capsule Network Architecture
verfasst von
Shubhranil Kundu
B. Gagana
Copyright-Jahr
2020
Verlag
Springer Singapore
DOI
https://doi.org/10.1007/978-981-15-0630-7_8

Neuer Inhalt