DEVELOPMENT OF LEARNING RULES FOR HIGH-ORDER CELLULAR NEURAL NETWORKS AND APPLICABILITY IN IMAGE PROCESSING
Keywords
DOI:
https://doi.org/10.34238/tnu-jst.8087Abstract
This paper aims at modifying a learning algorithm, developed from Recurrent Perceptron Learning Algorithm (RPLA) and a Pattern Recognition Algorithm for High-Order Cellular Neural Networks (HOCNN). Our research methods are developing theory of learning for high-order cellular neural networks and experiment with modified algorithms. The research results include two proposed algorithms and software which was built to test the two mentioned algorithms. The obtained set of the weights from our developed algorithm (named as Second-Order Recurrent Perceptron Learning Algorithm: SORPLA) can be used as filters or kernels for problems in imaging processing. In conclusion, firstly, the paper has modified the RPLA algorithm, which adds templates A and high-level templates B; secondly, it has improved the PyCNN image processing algorithm; finally, the paper also proposes an applicability of SORPLA in edge detection of image using the obtained set of the weights from the developed algorithm for the High-Order Cellular Neural Networks.Downloads
References
Wikipedia, "Cellular neural network," 2023. [Online]. Available: https://en.wikipedia.org/wiki/ Cellular_neural_network. [Accessed June 4, 2023].
A. Slavova, Cellular Neural Networks: Dynamics and Modelling, Springer Dordrecht, 2003.
D. Liang, J. Zhang, S. Jiang, X. Zhang, J. Wu, and Q. Sun, "Mobile Traffic Prediction Based on Densely Connected CNN for Cellular Networks in Highway Scenarios," in Proceedings of the 11th International Conference on Wireless Communications and Signal Processing (WCSP), Xi'an, China, 2019, doi: 10.1109/WCSP.2019.8927980.
C. GuKzelis, S. Karamamut, I0. Genc, "A Recurrent Perceptron Learning Algorithm for Cellular Neural Networks," Springer-Verlag, vol. 51, pp. 296-309, 1999.
A. Aggarwal, "GitHub: Let's build from here," 2014. [Online]. Available: https://github.com/ ankitaggarwal011/PyCNN. [Accessed June 2, 2023].
A. Fülöp and A. Horváth, "Application of Cellular Neural Networks in Semantic Segmentation," in Proceedings of the IEEE International Symposium on Circuits and Systems, Daegu, Korea, 2021, doi: 10.1109/ ISCAS51556.2021.9401249.
L. O. Chua and L. Yang, "Cellular Neural Networks: Theory," IEEE Transactions on Circuits and Systems, vol. 35, no. 10, pp. 1257 - 1272, 1988.
Q. H. Nguyen, T. T. Nguyen, and D. A. Duong, "Achitecture and Stability of the Second – Order Cellular Neural," UTEHY Jounal of Science and Technology, vol. 27, pp. 91-97, 2020.
D. A. Duong, Q. H. Nguyen, T. T. Nguyen, T. V. Q. Lai, and T. D. Hoang, "Development of Recurrent Perceptron Learning Algorithm for Second-Order Cellular Neural Networks," Measurement, Control, and Automation, vol. 3, no. 3, pp. 64-72, 2022.
T. T. Nguyen, "Development of Multi-Interaction Cellular Neural Networks and Applicability," PhD. thesis, Vietnam Research Institute of Electronics, Informatics and Automation, Hanoi, 2022.
T. T. Nguyen, Q. H. Nguyen, and D. A. Duong, "Associative Memory Using Second-Order Cellular Neural Networks," Journal of Science and Technology on Information and Communication, vol. 1, no. 4, pp. 116-121, 2022.
Q. H. Nguyen, "High-Order Hopfield Neural Network Stability and Applicability in Robot Control," PhD. Thesis, Institute Academy of Science and Technology, Hanoi, 1996.
H. Mizutani, "A New Learning Method for Multilayered Cellular Neural Networks," in Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and Their Applications, Rome, Italy, 1994, doi: 10.1109/CNNA.1994.381680.
D. A Duong, T. T. Nguyen, T. T. Nguyen, and Q. H. Nguyen, "Modified Perceptron Learning Rule and Application Abilities for Cellular Neural Networks," Scientific Journal of Ha Long Universities, vol. 6, no. 6, pp. 1-7, 2022.
K. Karacs, Gy. Cserey, Á. Zarándy, P. Szolgay, Cs. Rekeczky, L. Kék, and V. Szabó, "Software Library for Cellular Ware Computing Engines, Budapest, Hungary: Cellular Sensory and Wave Computing Laboratory of the Computer and Automation," 2014.
