Abstract
The paper describes a new extension of the convolutional neural network concept. The developed network, similarly to the CNN, instead of using independent weights for each neuron in the network uses related weights. This results in a small number of parameters optimized in the learning process, and high resistance to overtraining. However unlike the CNN, instead of sharing weights, the network takes advantage of weights correlated with coordinates of a neuron and its inputs, calculated by a dedicated subnet. This solution allows the neural layer of the network to perform global transformation of patterns what was unachievable for convolutional layers. The new network concept has been confirmed by verification of its ability to perform typical image affine transformations such as translation, scaling and rotation.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Jaderberg, M., Simonyan, K., Zisserman, A., Kavukcuoglu, K.: Spatial transformer networks. In: NIPS 2015 (Spotlight), vol. 2, pp. 2017–2025 (2015)
Ferreira, A., Giraldib, G.: Convolutional Neural Network approaches to granite tiles classification. Expert Syst. Appl. 84, 1–11 (2017)
Krizhevsky, A., Sutskever I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS-2012, pp. 1097–1105 (2012)
Zhang, Y., Zhao, D., Sun, J., Zou, G., Li, W.: Adaptive convolutional neural network and its application in face recognition. Neural Process. Lett. 43(2), 389–399 (2016)
Radwan, M.A., Khalil, M.I., Abbas, H.M.: Neural networks pipeline for offline machine printed Arabic OCR. Neural Process. Lett. (2017). https://doi.org/10.1007/s11063-017-9727-y
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR, abs/1409.1556. http://arxiv.org/abs/1409.1556. Accessed 19 May 2018
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient based learning applied to document recognition. IEEE 86(11), 2278–2324 (1998)
Abdel-Hamid, O., Mohamed, A., Jiang, H., Deng, L., Penn, G., Yu, D.: Convolutional Neural Networks for speech recognition. IEEE/ACM Trans. Audio Speech Lang. Process. 22(10), 1533–1545 (2014)
Wang, Y., Zu, C., Hu, G., et al.: Automatic tumor segmentation with Deep Convolutional Neural Networks for radiotherapy applications. Neural Process. Lett. (2018). https://doi.org/10.1007/s11063-017-9759-3
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323(6088), 533–536 (1986)
Golak, S.: Induced weights artificial neural network. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds.) ICANN 2005. LNCS, vol. 3697, pp. 295–300. Springer, Heidelberg (2005). https://doi.org/10.1007/11550907_47
Cire, D., Meier, U., Schmidhuber, J.: Multi-column deep neural networks for image classification. Arxiv preprint arXiv:1202.2745 (2012)
Christian, I., Husken, M.: Empirical evaluation of the improved Rprop learning algorithms. Neurocomputing 50, 105–123 (2003)
Nguyen, D., Widrow, B.: Improving the learning speed of 2-layer neural networks by choosing initial values of adaptive weights. In: IJCNN, pp. III-21–26 (1989)
Acknowledgments
This research was supported in part by PL-Grid Infrastructure under Grant PLGJAMA2017.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Golak, S., Jama, A., Blachnik, M., Wieczorek, T. (2018). New Architecture of Correlated Weights Neural Network for Global Image Transformations. In: Kůrková, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds) Artificial Neural Networks and Machine Learning – ICANN 2018. ICANN 2018. Lecture Notes in Computer Science(), vol 11140. Springer, Cham. https://doi.org/10.1007/978-3-030-01421-6_6
Download citation
DOI: https://doi.org/10.1007/978-3-030-01421-6_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-01420-9
Online ISBN: 978-3-030-01421-6
eBook Packages: Computer ScienceComputer Science (R0)