Abstract
Convolutional neural networks (CNNs) have been developed quickly in many real-world fields. However, CNN’s performance depends heavily on its hyperparameters, while finding suitable hyperparameters for CNNs working in application fields is challenging for three reasons: (1) the problem of mixed-variable encoding for different types of hyperparameters in CNNs, (2) expensive computational costs in evaluating candidate hyperparameter configuration, and (3) the problem of ensuring convergence rates and model performance during hyperparameter search. To overcome these problems and challenges, a hybrid-model optimization algorithm is proposed in this paper to search suitable hyperparameter configurations automatically based on the Gaussian process and particle swarm optimization (GPPSO) algorithm. First, a new encoding method is designed to efficiently deal with the CNN hyperparameter mixed-variable problem. Second, a hybrid-surrogate-assisted model is proposed to reduce the high cost of evaluating candidate hyperparameter configurations. Third, a novel activation function is suggested to improve the model performance and ensure the convergence rate. Intensive experiments are performed on image-classification benchmark datasets to demonstrate the superior performance of GPPSO over state-of-the-art methods. Moreover, a case study on metal fracture diagnosis is carried out to evaluate the GPPSO algorithm performance in practical applications. Experimental results demonstrate the effectiveness and efficiency of GPPSO, achieving accuracy of 95.26% and 76.36% only through 0.04 and 1.70 GPU days on the CIFAR-10 and CIFAR-100 datasets, respectively.
摘要
卷积神经网络(CNN)在许多实际应用领域中有着快速发展. 然而, CNN性能很大程度上取决于其超参数, 而为CNN配置合适的超参数通常面临着以下3个挑战: (1)不同类型CNN超参数的混合变量编码问题; (2)评估候选模型的昂贵计算成本问题; (3)确保搜索过程中收敛速率和模型性能问题. 针对上述问题, 提出一种基于高斯过程(GP)和粒子群优化算法(PSO)的混合模型优化算法(GPPSO), 用于自动搜索最优的CNN超参数配置. 首先, 设计一种新的编码方法高效编码CNN中不同类型的超参数. 其次, 提出一种混合代理辅助(HSA)模型降低评估候选模型的高计算成本. 最后, 设计一种新的激活函数改善模型性能并确保收敛速率. 在图像分类基准数据集上进行了大量实验, 验证GPPSO优于最先进的方法. 以金属断口诊断为例, 验证GPPSO算法在实际应用中的有效性. 实验结果表明, GPPSO仅需0.04和1.70 GPU天即可在CIFAR-10和CIFAR-100数据集上实现95.26%和76.36%识别准确率.
Similar content being viewed by others
Data availability
Due to the nature of this research, all authors of this paper did not agree for their data to be shared publicly, so supporting data are not available.
References
Abadi M, Agarwal A, Barham P, et al., 2016. Tensor-Flow: large-scale machine learning on heterogeneous distributed systems. https://arxiv.org/abs/1603.04467
Alvarez-Rodriguez U, Battiston F, de Arruda GF, et al., 2021. Evolutionary dynamics of higher-order interactions in social networks. Nat Hum Behav, 5(5):586–595. https://doi.org/10.1038/s41562-020-01024-1
Alzubaidi L, Zhang JL, Humaidi AJ, et al., 2021. Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. J Big Data, 8(1):53. https://doi.org/10.1186/s40537-021-00444-8
Baker B, Gupta O, Naik N, et al., 2017. Designing neural network architectures using reinforcement learning. https://arxiv.org/abs/1611.02167
Cai H, Chen TY, Zhang WN, et al., 2018. Efficient architecture search by network transformation. Proc 32nd AAAI Conf on Artificial Intelligence, p.2787–2794. https://doi.org/10.1609/aaai.v32i1.11709
Chen ZG, Zhan ZH, Kwong S, et al., 2022. Evolutionary computation for intelligent transportation in smart cities: a survey. IEEE Comput Intell Mag, 17(2):83–102. https://doi.org/10.1109/MCI.2022.3155330
Darwish A, Hassanien AE, Das S, 2020. A survey of swarm and evolutionary computing approaches for deep learning. Artif Intell Rev, 53(3):1767–1812. https://doi.org/10.1007/s10462-019-09719-2
Fernandes FE, Yen GG, 2021. Automatic searching and pruning of deep neural networks for medical imaging diagnostic. IEEE Trans Neur Netw Learn Syst, 32(12):5664–5674. https://doi.org/10.1109/TNNLS.2020.3027308
Fielding B, Lawrence T, Zhang L, 2019. Evolving and ensembling deep CNN architectures for image classification. Int Joint Conf on Neural Networks, p.1–8. https://doi.org/10.1109/IJCNN.2019.8852369
Goodfellow IJ, Warde-Farley D, Mirza M, et al., 2013. Maxout networks. Proc 30th Int Conf on Machine Learning, p.1319–1327.
Grigorescu S, Trasnea B, Cocias T, et al., 2020. A survey of deep learning techniques for autonomous driving. J Field Robot, 37(3):362–386. https://doi.org/10.1002/rob.21918
Guo H, Zhang W, Nie XY, et al., 2022. High-speed planar imaging of OH radicals in turbulent flames assisted by deep learning. Appl Phys B, 128(3):52. https://doi.org/10.1007/s00340-021-07742-2
He KM, Zhang XY, Ren SQ, et al., 2016. Deep residual learning for image recognition. IEEE Conf on Computer Vision and Pattern Recognition, p.770–778. https://doi.org/10.1109/CVPR.2016.90
Huang G, Liu Z, van der Maaten L, et al., 2017. Densely connected convolutional networks. 30th IEEE Conf on Computer Vision and Pattern Recognition, p.2261–2269. https://doi.org/10.1109/CVPR.2017.243
Jiang WW, Luo JY, 2022. Graph neural network for traffic forecasting: a survey. Expert Syst Appl, 207:117921. https://doi.org/10.1016/j.eswa.2022.117921
Jin HF, Song QQ, Hu X, 2019. Auto-Keras: an efficient neural architecture search system. Proc 25th ACM SIGKDD Int Conf on Knowledge Discovery & Data Mining, p.1946–1956. https://doi.org/10.1145/3292500.3330648
Krizhevsky A, Sutskever I, Hinton GE, 2017. ImageNet classification with deep convolutional neural networks. Commun ACM, 60(6):84–90. https://doi.org/10.1145/3065386
Larsson G, Maire M, Shakhnarovich G, 2016. FractalNet: ultra-deep neural networks without residuals. https://arxiv.org/abs/1605.07648
Li JY, Zhan ZH, Wang C, et al., 2020. Boosting data-driven evolutionary algorithm with localized data generation. IEEE Trans Evol Comput, 24(5):923–937. https://doi.org/10.1109/TEVC.2020.2979740
Li JY, Zhan ZH, Liu RD, et al., 2021. Generation-level parallelism for evolutionary computation: a pipeline-based parallel particle swarm optimization. IEEE Trans Cybern, 51(10):4848–4859. https://doi.org/10.1109/TCYB.2020.3028070
Li JY, Zhan ZH, Zhang J, 2022. Evolutionary computation for expensive optimization: a survey. Mach Intell Res, 19(1):3–23. https://doi.org/10.1007/s11633-022-1317-4
Li JY, Zhan ZH, Xu J, et al., 2023. Surrogate-assisted hybridmodel estimation of distribution algorithm for mixed-variable hyperparameters optimization in convolutional neural networks. IEEE Trans Neur Netw Learn Syst, 34(5):2338–2352. https://doi.org/10.1109/TNNLS.2021.3106399
Li X, Lai SQ, Qian XM, 2022. DBCFace: towards pure convolutional neural network face detection. IEEE Trans Circ Syst Video Technol, 32(4):1792–1804. https://doi.org/10.1109/TCSVT.2021.3082635
Lin M, Chen Q, Yan SC, 2013. Network in network. https://arxiv.org/abs/1312.4400
Liu HX, Simonyan K, Vinyals O, et al., 2017. Hierarchical representations for efficient architecture search. https://arxiv.org/abs/1711.00436
Miranda LJV, 2018. PySwarms: a research toolkit for particle swarm optimization in Python. J Open Source Softw, 3(21):433. https://doi.org/10.21105/joss.00433
Poli R, Kennedy J, Blackwell T, 2007. Particle swarm optimization. Swarm Intell, 1(1):33–57. https://doi.org/10.1007/s11721-007-0002-0
Real E, Moore S, Selle A, et al., 2017. Large-scale evolution of image classifiers. https://arxiv.org/abs/1703.01041v2
Simonyan K, Zisserman A, 2014. Very deep convolutional networks for large-scale image recognition. https://arxiv.org/abs/1409.1556
Snoek J, Larochelle H, Adams RP, 2012. Practical Bayesian optimization of machine learning algorithms. https://arxiv.org/abs/1206.2944
Springenberg JT, Dosovitskiy A, Brox T, et al., 2014. Striving for simplicity: the all convolutional net. https://arxiv.org/abs/1412.6806v3
Srivastava RK, Greff K, Schmidhuber J, 2015. Highway networks. https://arxiv.org/abs/1505.00387
Suganuma M, Shirakawa S, Nagao T, 2017. A genetic programming approach to designing convolutional neural network architectures. Proc Genetic and Evolutionary Computation Conf, p.497–504. https://doi.org/10.1145/3071178.3071229
Sun YN, Xue B, Zhang MJ, et al., 2019. A particle swarm optimization-based flexible convolutional autoencoder for image classification. IEEE Trans Neur Netw Learn Syst, 30(8):2295–2309. https://doi.org/10.1109/TNNLS.2018.2881143
Sun YN, Xue B, Zhang MJ, et al., 2020a. Automatically designing CNN architectures using the genetic algorithm for image classification. IEEE Trans Cybern, 50(9):3840–3854. https://doi.org/10.1109/TCYB.2020.2983860
Sun YN, Xue B, Zhang M, et al., 2020b. Completely automated CNN architecture design based on blocks. IEEE Trans Neur Netw Learn Syst, 31(4):1242–1254. https://doi.org/10.1109/TNNLS.2019.2919608
Sun YN, Wang HD, Xue B, et al., 2020c. Surrogate-assisted evolutionary deep learning using an end-to-end random forest-based performance predictor. IEEE Trans Evol Comput, 24(2):350–364. https://doi.org/10.1109/TEVC.2019.2924461
Tulbure AA, Tulbure AA, Dulf EH, 2022. A review on modern defect detection models using DCNNs-deep convolutional neural networks. J Adv Res, 35:33–48. https://doi.org/10.1016/j.jare.2021.03.015
Wang B, Sun YN, Xue B, et al., 2018. Evolving deep convolutional neural networks by variable-length particle swarm optimization for image classification. IEEE Congress on Evolutionary Computation, p.1–8. https://doi.org/10.1109/CEC.2018.8477735
Wang B, Xue B, Zhang MJ, 2020. Particle swarm optimisation for evolving deep neural networks for image classification by evolving and stacking transferable blocks. IEEE Congress on Evolutionary Computation, p.1–8. https://doi.org/10.1109/CEC48606.2020.9185541
Wang YQ, Li JY, Chen CH, et al., 2022. Scale adaptive fitness evaluation-based particle swarm optimisation for hyperparameter and architecture optimisation in neural networks and deep learning. CAAI Trans Intell Technol, early access. https://doi.org/10.1049/cit2.12106
Wu SH, Zhan ZH, Tan KC, et al., 2023. Orthogonal transfer for multitask optimization. IEEE Trans Evol Comput, 27(1):185–200. https://doi.org/10.1109/TEVC.2022.3160196
Wu T, Shi J, Zhou DY, et al., 2019. A multi-objective particle swarm optimization for neural networks pruning. IEEE Congress on Evolutionary Computation, p.570–577. https://doi.org/10.1109/CEC.2019.8790145
Xie LX, Yuille A, 2017. Genetic CNN. IEEE Int Conf on Computer Vision, p.1388–1397. https://doi.org/10.1109/ICCV.2017.154
Zhan ZH, Li JY, Zhang J, 2022a. Evolutionary deep learning: a survey. Neurocomputing, 483:42–58. https://doi.org/10.1016/j.neucom.2022.01.099
Zhan ZH, Zhang J, Lin Y, et al., 2022b. Matrix-based evolutionary computation. IEEE Trans Emerg Top Comput Intell, 6(2):315–328. https://doi.org/10.1109/TETCI.2020.3047410
Zhong Z, Yan JJ, Wu W, et al., 2018. Practical block-wise neural network architecture generation. IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.2423–2432. https://doi.org/10.1109/CVPR.2018.00257
Zoph B, Le QV, 2017. Neural architecture search with reinforcement learning. https://arxiv.org/abs/1611.01578
Author information
Authors and Affiliations
Contributions
Han YAN designed the research and performed the experiments. Han YAN and Chongquan ZHONG implemented the software and drafted the paper. Yuhu WU, Liyong ZHANG, and Wei LU revised and finalized the paper.
Corresponding author
Ethics declarations
Han YAN, Chongquan ZHONG, Yuhu WU, Liyong ZHANG, and Wei LU declare that they have no conflict of interest.
Additional information
Project supported by the National Natural Science Foundation of China (Nos. 62073056 and 61876029), the Applied Basic Research Project of Liaoning Province, China (No. 2023JH2/101300207), and the Key Field Innovation Team Project of Dalian, China (No. 2021RT14)
Rights and permissions
About this article
Cite this article
Yan, H., Zhong, C., Wu, Y. et al. A hybrid-model optimization algorithm based on the Gaussian process and particle swarm optimization for mixed-variable CNN hyperparameter automatic search. Front Inform Technol Electron Eng 24, 1557–1573 (2023). https://doi.org/10.1631/FITEE.2200515
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1631/FITEE.2200515
Key words
- Convolutional neural network
- Gaussian process
- Hybrid model
- Hyperparameter optimization
- Mixed-variable
- Particle swarm optimization