Abstract
Although CNN-GA [1] is totally automated, the generated architectures have a restricted connectional structure since it employs an encoding strategy that encodes the building blocks into a linked list that can be extended to any depth during the process of evolution. Each linked list encoding building block is a “skip layer” or a pooling layer, where the skip layer containing a skip connection and two convolutional layers [1].
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Sun, Y., Xue, B., Zhang, M., Yen, G. G., & Lv, J. (2020b). Automatically designing cnn architectures using the genetic algorithm for image classification. IEEE Transactions on Cybernetics, 50(9), 3840–3854.
He, K., Zhang, X., Ren, S., & Sun, J. (2016a). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 770–778).
Zhong, Z., Yan, J., & Liu, C.-L. (2018). Practical network blocks design with q-learning. In Proceedings of the 2018 AAAI Conference on Artificial Intelligence.
Huang, G., Liu, Z., Weinberger, K. Q., & van der Maaten, L. (2017). Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 4700–4708).
Glorot, X., Bordes, A., & Bengio, Y. (2011). Deep sparse rectifier neural networks. In Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics (pp. 315–323).
Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Proceedings of the 32nd International Conference on Machine Learning, Volume 37 of Proceedings of Machine Learning Research (pp. 448–456). PMLR.
Suganuma, M., Shirakawa, S., & Nagao, T. (2018). A genetic programming approach to designing convolutional neural network architectures. In Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI-18 (pp. 5369–5373). https://doi.org/10.24963/ijcai.2018/755.
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of CVPR (pp. 2818–2826).
Krizhevsky, A. (2009). Learning multiple layers of features from tiny images. Technical Report, University of Toronto. https://www.cs.toronto.edu/~kriz/learning-features-2009-TR.pdf.
Zhu, Y., Yao, Y., Wu, Z., Chen, Y., Li, G., Hu, H., Xu, Y. (2018). Gp-cnas: Convolutional neural network architecture search with genetic programming. arXiv:1812.07611.
Bottou, L. (2012). Stochastic gradient descent tricks. In Neural networks: Tricks of the trade (2nd ed.) (pp. 421–436). Springer. ISBN 978-3-642-35289-8. https://doi.org/10.1007/978-3-642-35289-8_25.
Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. In Proceedings of the 32nd International Conference on Machine Learning.
Liu, H., Simonyan, K., Vinyals, O., Fernand C., & Kavukcuoglu, K. (2017b). Hierarchical representations for efficient architecture search. arXiv:1711.00436.
Xie, L., & Yuille, A. L. (2017). Genetic CNN. In IEEE International Conference on Computer Vision, ICCV 2017 (pp. 1388–1397). https://doi.org/10.1109/ICCV.2017.154.
Real, E., Moore, S., Selle, A., Saxena, S., Suematsu, Y. L., Tan, J., Le, Q., & Kurakin, A. (2017). Large-scale evolution of image classifiers (pp. 2902–2911).
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). Encoding Space Based on Directed Acyclic Graphs. 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_13
Download citation
DOI: https://doi.org/10.1007/978-3-031-16868-0_13
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)