Abstract
Correlated weights neural layers (CWNL) extend the concept of weight sharing present in the convolution layers by using neural subnetworks that dynamically calculate multiple weights and biases as a function of the position of a neuron and its inputs. By using, in contrast to the convolutional layer, absolute coordinates of the neuron and inputs and a universal approximator instead of a static kernel matrix, this type of layer allows for global, parametric, and nonlinear operations on the image. The article presents a mathematical model of such a layer and the methodology of its training. The advantage of networks using CWNL layers was demonstrated on the example of the nonlinear transformation of images from the MNIST set and generation of synthetic images based on Bezier curves.
This research was supported by grants of Silesian University of Technology (11/040/RGJ20/0017 and 11/040/BK21/0023) and by PLGrid Infrastructure.
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
Similar content being viewed by others
References
Dhillon, A., Verma, G.K.: Convolutional neural network: a review of models, methodologies and applications to object detection. Prog. Artif. Intell. 9(2), 85–112 (2020)
Yao, G., Lei, T., Zhong, J.: A review of convolutional-neural-network-based action recognition. Pattern Recogn. Lett. 118, 14–22 (2019)
Silver, D., et al.: Mastering the game of go without human knowledge. Nature 550(7676), 354–359 (2017)
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
Golak, S., Jama, A., Blachnik, M., Wieczorek, T.: New architecture of correlated weights neural network for global image transformations. In: Kůrková, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds.) ICANN 2018. LNCS, vol. 11140, pp. 56–65. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01421-6_6
Jaderberg, M., Simonyan, K., Zisserman, A., Kavukcuoglu, K.: Spatial transformer networks. In: NIPS 2015 (Spotlight), vol. 2, pp. 2017–2025 (2015)
Riedmiller, M., Braun, H.: RPROP-a fast adaptive learning algorithm. In: Proceedings of ISCIS VII), Universitat (1992)
Chollet, F.: Building autoencoders in keras. The Keras Blog 14 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Golak, S. (2021). Nonlinear Parametric Transformation and Generation of Images Based on a Network with the CWNL Layer. In: Pham, D.N., Theeramunkong, T., Governatori, G., Liu, F. (eds) PRICAI 2021: Trends in Artificial Intelligence. PRICAI 2021. Lecture Notes in Computer Science(), vol 13033. Springer, Cham. https://doi.org/10.1007/978-3-030-89370-5_31
Download citation
DOI: https://doi.org/10.1007/978-3-030-89370-5_31
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-89369-9
Online ISBN: 978-3-030-89370-5
eBook Packages: Computer ScienceComputer Science (R0)