Abstract
One of the main topics of human science research is to explain the mechanism of brain activity and the essence of human intelligence, create intelligent machines similar to human intelligent activities, and develop the technology and intelligent application of human intelligence. The research on pattern recognition using CNN technology is a hot topic. Therefore, this paper studies the problems faced by pattern recognition and explores it. Firstly, this paper discusses the research background and significance of CNN, and briefly introduces the characteristics of CNN. Then it summarizes the relevant articles at home and abroad. Then it briefly describes the BP neural model used in eep and its existing reasons, and explains the better effects they may bring. Finally, a series of experimental tests are carried out on pattern recognition. It is concluded that the network with scaling parameter set to 4 and depth of about 26 has the best effect, which can effectively solve the problem of pattern recognition.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Li, D., Zhao, X., Yuan, G., Liu, Y., Liu, G.: Robustness comparison between the capsule network and the convolutional network for facial expression recognition. Appl. Intell. 51(4), 2269–2278 (2020). https://doi.org/10.1007/s10489-020-01895-x
Kong, Q., Cao, Y., Iqbal, T., et al.: PANNs: large-scale pretrained audio neural networks for audio pattern recognition. IEEE/ACM Trans. Audio Speech Lang. Process. 28, 2880–2894 (2020)
Dai, Y., Qiu, D., Wang, Y., et al.: Research on computer-aided diagnosis of Alzheimer’s disease based on heterogeneous medical data fusion. Int. J. Pattern Recogn. Artif. Intell. 33(5), 1957001.1–1957001.17 (2019)
Zhang, Q., Zhang, M., Chen, T., et al.: Recent advances in Convolutional Neural Network acceleration. Neurocomputing 323, 37–51 (2019)
Ahmed, T., Parvin, M.S., Haque, M.R., et al.: Lung cancer detection using CT image based on 3D CNN. Comput. Commun. (English) 3, 35–42 (2020)
Afridi, M.J., et al.: On automated source selection for transfer learning in CNNs. Pattern Recogn. J. Pattern Recogn. Soc. 73, 65–75 (2018)
Nguyen, H.D., Yeom, S., Lee, G.S., et al.: Facial emotion recognition using an ensemble of multi-level CNNs. Int. J. Pattern Recogn. Artif. Intell. 33(11), 139–149 (2018)
Banharnsakun, A.: Towards improving the Convolutional Neural Networks for deep learning using the distributed artificial bee colony method. Int. J. Mach. Learn. Cybern. 10(6), 1301–1311 (2019)
Liu, W., Wang, Z., Liu, X., et al.: A survey of deep neural network architectures and their applications. Neurocomputing 234, 11–26 (2017)
Zahangir, A.M., Mahmudul, H., Chris, Y., et al.: Improved inception-residual convolutional neural network for object recognition. Neural Comput. Appl. 32, 1–15 (2017)
Wu, Z., Jiang, S., Zhou, X., et al.: Application of image retrieval based on Convolutional Neural Networks and Hu invariant moment algorithm in computer telecommunications. Comput. Commun. 150, 729–738 (2020)
Ashiquzzaman, A., Tushar, A.K.: Handwritten Arabic numeral recognition using deep learning neural networks. In: IEEE 2017 IEEE International Conference on Imaging, Vision & Pattern Recognition (icIVPR) - Dhaka, Bangladesh, 13–14 February 2017, pp. 1–4 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sun, Z. (2022). Pattern Recognition in Convolutional Neural Network (CNN). In: Sugumaran, V., Sreedevi, A.G., Xu , Z. (eds) Application of Intelligent Systems in Multi-modal Information Analytics. ICMMIA 2022. Lecture Notes on Data Engineering and Communications Technologies, vol 138. Springer, Cham. https://doi.org/10.1007/978-3-031-05484-6_37
Download citation
DOI: https://doi.org/10.1007/978-3-031-05484-6_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-05483-9
Online ISBN: 978-3-031-05484-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)