Abstract
Machine Learning experts spend much time on fine-tuning. A methodology that automatically searches neural architectures has been to solve this problem. Differentiable Architecture Search (DARTS) is an algorithm that solves a Neural Architecture Search problem using a gradient-based approach. We found an architecture that shows higher test accuracy than the existing DARTS architecture with the DARTS algorithm on the CIFAR-10 dataset. The architecture performed the DARTS algorithm several times and recorded the highest test accuracy of 97.62%. This result exceeds the test accuracy of 97.24 ± 0.09 shown in the existing DARTS paper. These results are expected to raise the baseline for making a practical difference in the study of Neural Architecture Search.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Thomas, E., Jan, H.M., Frank, H.: Neural architecture search: a survey. J. Mach. Learn. Res. 20, 1–21 (2019)
Barret, Z., Quoc, V.L.: Neural architecture search with reinforcement learning. In: International Conference on Learning Representations, ICLR, Toulon (2017)
Hieu, P., Melody, Y.G., Barret, Z., Quoc, V.L., Jeff, D.: Efficient neural architecture search via parameter sharing. In: International Conference on Machine Learning, ICML, Stockholm (2018)
Xin, Y.: Evolving artificial neural networks. IEEE Trans. Neural Netw. 8, 694–713 (1997)
Hanxiao, L., Karen, S., Yiming, Y.: Differentiable architecture search. In: International Conference on Learning Representations, ICLR, New Orleans (2019)
Barret, Z., Vijay, V., Jonathon, S., Quoc, V.L.: Learning transferable architectures. In: Computer Vision and Pattern Recognition, CVPR, Salt Lake City (2018)
Esteban, R., Alok, A., Yanping, H., Quoc, V.L.: Regularized evolution for image classifier architecture search. In: AAAI Conference on Artificial Intelligence, AAAI, Hawaii (2019)
Gabriel, B., Pieter-Jan, K., Barret, Z., Vijay, V., Quoc, L.: Understanding and simplifying one-shot architecture search. In: International Conference on Machine Learning, ICML, Stockholm, pp. 549–558 (2018)
Andrew, B., Theodore, L., James, M.R., Nick, W.: Smash: one-shot model architecture search through hypernetworks. In: International Conference on Learning Representations, ICLR, Vancouver (2018)
Chen, X., Xie, L., Wu, J., Tian, Q.: Progressive DARTS: bridging the optimization gap for NAS in the wild. Int. J. Comput. Vis. 129(3), 638–655 (2020). https://doi.org/10.1007/s11263-020-01396-x
Peng, Y., Baopu, L., Yikang, L., Tao, C., Jiayuan, F., Wanli, O.: b-DARTS: beta-decay regularization for differentiable architecture search. In: Proceedings of the IEEE/CVF Computer Vision and Pattern Recognition Conference, CVPR, New Orleans, pp. 10874–10883 (2022)
Terrance, D., Graham, W.T.: Improved regularization of convolutional neural networks with cutout. arXiv preprint https://arxiv.org/abs/1708.04552 (2017)
Kaiming, H., Xiangyu, Z., Shaoqing, R., Jian, S.: Deep residual learning for image recognition. In: Computer Vision and Pattern Recognition, CVPR, Boston (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Shin, J.Y., Kang, DK. (2023). A Higher Performing DARTS Model for CIFAR-10. In: Zaynidinov, H., Singh, M., Tiwary, U.S., Singh, D. (eds) Intelligent Human Computer Interaction. IHCI 2022. Lecture Notes in Computer Science, vol 13741. Springer, Cham. https://doi.org/10.1007/978-3-031-27199-1_10
Download citation
DOI: https://doi.org/10.1007/978-3-031-27199-1_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-27198-4
Online ISBN: 978-3-031-27199-1
eBook Packages: Computer ScienceComputer Science (R0)