Abstract
There has been a large number of research done to enhance utilizing EC for an evolved CNN architecture, but there has not been much study on using other EC approaches to develop CNN architectures, as a result, some other significant EC approaches are anticipated to be investigated for evolving CNN architectures without involving humans. PSO is chosen in this chapter because it has the benefits over traditional implementation, reduced computing cost, less parameters to tweak, and it has never been used to create the architectures of CNNs. However, because the best CNN architecture differs for different problems, the fixed-length encoding of particles in conventional PSO poses a significant problem for evolving CNN architectures, therefore a unique flexible encoding method is designed to overcome the fixed-length limitation, it is the most basic aspect of the work in this chapter.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Postel, J. (1980). Dod standard internet protocol. ACM SIGCOMM Computer Communication Review, 10(4), 12–51.
Fuller, V., Li, T., Yu, J., & Varadhan, K. (1993). Classless inter-domain routing (cidr): An address assignment and aggregation strategy.
Glorot, X., & Bengio, Y. (2010). Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the 13th International Conference on Artificial Intelligence and Statistics (pp. 249–256).
Chan, T.-H., Jia, K., Gao, S., Jiwen, L., Zeng, Z., & Ma, Y. (2015). Pcanet: A simple deep learning baseline for image classification? IEEE Transactions on Image Processing, 24(12), 5017–5032.
Sohn, K., & Lee, H. (2012). Learning invariant representations with local transformations. https://arxiv.org/abs/1206.6418.
Rifai, S., Vincent, P., Muller, X., Glorot, X., & Bengio, Y. (2011). Contractive auto-encoders: Explicit invariance during feature extraction. In Proceedings of the 28th International Conference on Machine Learning (pp. 833–840).
Bruna, J., & Mallat, S. (2013). Invariant scattering convolution networks. IEEE transactions on Pattern Analysis and Machine Intelligence, 35(8), 1872–1886. https://doi.org/10.1109/tpami.2012.230.
Sohn K., Zhou G., Lee C., & Lee H. (2013). Learning and selecting features jointly with point-wise gated boltzmann machines. https://dl.acm.org/citation.cfm?id=3042918.
Larochelle, H., Erhan, D., Courville, A., Bergstra, J., & Bengio, Y. (2007). An empirical evaluation of deep architectures on problems with many factors of variation. In Proceedings of the 24th international conference on Machine learning (pp. 473–480). ACM. https://doi.org/10.1145/1273496.1273556.
Hinton, G. E. (2012). A practical guide to training restricted boltzmann machines. In Neural networks: Tricks of the trade (pp. 599–619). Springer.
Van den Bergh, F., & Engelbrecht, A. P. (2006). A study of particle swarm optimization particle trajectories. Information Sciences, 176(8), 937–971. https://doi.org/10.1016/j.ins.2005.02.003.
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M. et al. (2016). Tensorflow: Large-scale machine learning on heterogeneous distributed systems. ar**v:1603.04467.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Sun, Y., Yen, G.G., Zhang, M. (2023). Internet Protocol Based Architecture Design. In: Evolutionary Deep Neural Architecture Search: Fundamentals, Methods, and Recent Advances. Studies in Computational Intelligence, vol 1070. Springer, Cham. https://doi.org/10.1007/978-3-031-16868-0_10
Download citation
DOI: https://doi.org/10.1007/978-3-031-16868-0_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-16867-3
Online ISBN: 978-3-031-16868-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)