{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:24:30Z","timestamp":1777569870406,"version":"3.51.4"},"reference-count":78,"publisher":"Walter de Gruyter GmbH","issue":"4","license":[{"start":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T00:00:00Z","timestamp":1752192000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Deep neural networks (DNNs) are now widely used in numerous fields. However, manually design-ing DNNs is labor-intensive and requires expert knowledge. Evolutionary neural architecture search (ENAS) is an efficient method. Nevertheless, ENAS requires full-epoch training for each candidate architecture to determine fitness values, leading to high computational costs. To accelerate the search process and reduce resource consumption, this paper proposes MFGENAS, an accelerated ENAS method. MFGENAS is implemented within the NSGA-II framework and employs two key acceleration strategies: multi-fidelity evaluation and a genetic decision controller. We demonstrate through experi-mental analysis that classification-based prediction is significantly more effective than regression-based prediction in estimating architecture performance. To reduce the need for expensive evaluations, we introduce a genetic decision controller to evaluate the quality of generated offspring. This process is treated as a classification task: if the controller predicts that the offspring will outperform the parent, the offspring is retained. For this purpose, we adopt a kernel extreme learning machine optimized by an improved polar lights optimizer as the genetic decision controller. Comprehensive experiments vali-date MFGENAS\u2019s performance. On the CIFAR-10 dataset, MFGENAS discovers an architecture with an error rate of 2.39% using only 0.3 GPU days. In contrast, the classical AE-CNN requires 27 GPU days to achieve an architecture with a higher error rate of 4.30%. On the CIFAR-100 dataset, MFGENAS discovers an architecture with an error rate of 16.42% in just 0.3 GPU days, whereas E2EPP requires 8.5 GPU days to reach an error rate of 22.02%.<\/jats:p>","DOI":"10.2478\/jaiscr-2025-0020","type":"journal-article","created":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T08:12:49Z","timestamp":1752221569000},"page":"413-446","source":"Crossref","is-referenced-by-count":0,"title":["An Evolutionary Neural Architecture Search Method Accelerated by Multi-Fidelity Evaluation and Genetic Decision Controller"],"prefix":"10.2478","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3793-7150","authenticated-orcid":false,"given":"Zenglin","family":"Qiao","sequence":"first","affiliation":[{"name":"School of Mathematical Sciences , Beijing University of Posts and Telecommunications , Beijing , China"},{"name":"Key Laboratory of Mathematics and Information Networks ( Beijing University of Posts and Telecommunications ), Ministry of Education , China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6938-9948","authenticated-orcid":false,"given":"Ali Asghar","family":"Heidari","sequence":"additional","affiliation":[{"name":"School of Surveying and Geospatial Engineering, College of Engineering , University of Tehran , Tehran , Iran"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9376-7646","authenticated-orcid":false,"given":"Xinchao","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Mathematical Sciences , Beijing University of Posts and Telecommunications , Beijing , China"},{"name":"Key Laboratory of Mathematics and Information Networks ( Beijing University of Posts and Telecommunications ), Ministry of Education , China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7714-9693","authenticated-orcid":false,"given":"Huiling","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Artificial Intelligence , Wenzhou University , Wenzhou , China"}]}],"member":"374","published-online":{"date-parts":[[2025,7,11]]},"reference":[{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_001","doi-asserted-by":"crossref","unstructured":"N. H. Luong, Q. M. Phan, A. Vo, T. N. Pham, and D. T. Bui, \u201cLightweight multi-objective evolutionary neural architecture search with low-cost proxy metrics,\u201d Information Sciences, vol. 655, p. 119856, 2024\/01\/01\/2024, doi: https:\/\/doi.org\/10.1016\/j.ins.2023.119856.","DOI":"10.1016\/j.ins.2023.119856"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_002","doi-asserted-by":"crossref","unstructured":"X. Ma, W. Tang, P. Wang, X. Guo, and L. Gao, \u201cExtracting stage-specific and dynamic modules through analyzing multiple networks associated with cancer progression,\u201d IEEE\/ACM transactions on computational biology and bioinformatics, vol. 15, no. 2, pp. 647-658, 2016.","DOI":"10.1109\/TCBB.2016.2625791"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_003","doi-asserted-by":"crossref","unstructured":"J. Huang et al., \u201cDeep reinforcement learning-based trajectory pricing on ride-hailing platforms,\u201d ACM Transactions on Intelligent Systems and Technology (TIST), vol. 13, no. 3, pp. 1-19, 2022.","DOI":"10.1145\/3474841"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_004","doi-asserted-by":"crossref","unstructured":"Z. Song et al., \u201cRobustness-aware 3d object detection in autonomous driving: A review and outlook,\u201d IEEE Transactions on Intelligent Transportation Systems, 2024.","DOI":"10.1109\/TITS.2024.3439557"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_005","doi-asserted-by":"crossref","unstructured":"C. Hema and F. P. G. Marquez, \u201cEmotional speech recognition using cnn and deep learning techniques,\u201d Applied Acoustics, vol. 211, p. 109492, 2023.","DOI":"10.1016\/j.apacoust.2023.109492"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_006","doi-asserted-by":"crossref","unstructured":"V. Uc-Cetina, N. Navarro-Guerrero, A. Martin-Gonzalez, C. Weber, and S. Wermter, \u201cSurvey on reinforcement learning for language processing,\u201d Artificial Intelligence Review, vol. 56, no. 2, pp. 1543-1575, 2023.","DOI":"10.1007\/s10462-022-10205-5"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_007","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, and J. Sun, \u201cDeep residual learning for image recognition,\u201d in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770-778, 2016.","DOI":"10.1109\/CVPR.2016.90"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_008","doi-asserted-by":"crossref","unstructured":"G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, \u201cDensely connected convolutional networks,\u201d in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4700-4708, 2017.","DOI":"10.1109\/CVPR.2017.243"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_009","doi-asserted-by":"crossref","unstructured":"C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, \u201cRethinking the inception architecture for computer vision,\u201d in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2818-2826, 2016.","DOI":"10.1109\/CVPR.2016.308"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_010","doi-asserted-by":"crossref","unstructured":"B. Zoph, V. Vasudevan, J. Shlens, and Q. V. Le, \u201cLearning transferable architectures for scalable image recognition,\u201d in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 8697-8710, 2018.","DOI":"10.1109\/CVPR.2018.00907"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_011","doi-asserted-by":"crossref","unstructured":"Y. Chen et al., \u201cRenas: Reinforced evolutionary neural architecture search,\u201d in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 4787-4796, 2019.","DOI":"10.1109\/CVPR.2019.00492"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_012","doi-asserted-by":"crossref","unstructured":"B. Lyu et al., \u201cEfficient multi-objective neural architecture search framework via policy gradient algorithm,\u201d Information Sciences, vol. 661, p. 120186, 2024\/03\/01\/2024, doi: https:\/\/doi.org\/10.1016\/j.ins.2024.120186.","DOI":"10.1016\/j.ins.2024.120186"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_013","doi-asserted-by":"crossref","unstructured":"Y. Shen et al., \u201cProxybo: Accelerating neural architecture search via bayesian optimization with zero-cost proxies,\u201d in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, no. 8, pp. 9792-9801, 2023.","DOI":"10.1609\/aaai.v37i8.26169"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_014","doi-asserted-by":"crossref","unstructured":"H. Jin, Q. Song, and X. Hu, \u201cAuto-keras: An efficient neural architecture search system,\u201d in Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, pp. 1946-1956, 2019.","DOI":"10.1145\/3292500.3330648"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_015","doi-asserted-by":"crossref","unstructured":"N. Sinha and K.-W. Chen, \u201cNeural Architecture Search Using Covariance Matrix Adaptation Evolution Strategy,\u201d Evolutionary Computation, vol. 32, no. 2, pp. 177-204, 2024, doi: 10.1162\/evco a 00331.","DOI":"10.1162\/evco_a_00331"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_016","doi-asserted-by":"crossref","unstructured":"Y. Li, R. Liu, X. Hao, R. Shang, P. Zhao, and L. Jiao, \u201cEQNAS: Evolutionary Quantum Neural Architecture Search for Image Classification,\u201d Neural Networks, vol. 168, pp. 471-483, 2023\/11\/01\/2023, doi: https:\/\/doi.org\/10.1016\/j.neunet.2023.09.040.","DOI":"10.1016\/j.neunet.2023.09.040"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_017","doi-asserted-by":"crossref","unstructured":"S. Xiao, B. Zhao, and D. Liu, \u201cSemi-supervised accuracy predictor-based multi-objective neural architecture search,\u201d Neurocomputing, vol. 609, p. 128472, 2024\/12\/07\/2024, doi: https:\/\/doi.org\/10.1016\/j.neucom.2024.128472.","DOI":"10.1016\/j.neucom.2024.128472"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_018","doi-asserted-by":"crossref","unstructured":"Q. M. Phan and N. H. Luong, \u201cEnhancing multi-objective evolutionary neural architecture search with training-free Pareto local search,\u201d Applied Intelligence, vol. 53, no. 8, pp. 8654-8672, 2023\/04\/01 2023, doi: 10.1007\/s10489-022-04032-y.","DOI":"10.1007\/s10489-022-04032-y"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_019","doi-asserted-by":"crossref","unstructured":"L. Xu, J. Zheng, C. He, J. Wang, B. Zheng, and J. Lv, \u201cAdaptive Multi-particle Swarm Neural Architecture Search for High-incidence Cancer Prediction,\u201d IEEE Transactions on Artificial Intelligence, 2025.","DOI":"10.1109\/TAI.2025.3543822"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_020","doi-asserted-by":"crossref","unstructured":"L. Wen, L. Gao, X. Li, and H. Li, \u201cA new genetic algorithm based evolutionary neural architecture search for image classification,\u201d Swarm and Evolutionary Computation, vol. 75, p. 101191, 2022.","DOI":"10.1016\/j.swevo.2022.101191"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_021","doi-asserted-by":"crossref","unstructured":"V. Lopes, M. Santos, B. Degardin, and L. A. Alexandre, \u201cGuided evolutionary neural architecture search with efficient performance estimation,\u201d Neurocomputing, vol. 584, p. 127509, 2024\/06\/01\/2024, doi: https:\/\/doi.org\/10.1016\/j.neucom.2024.127509.","DOI":"10.1016\/j.neucom.2024.127509"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_022","doi-asserted-by":"crossref","unstructured":"J. Liu, R. Cheng, and Y. Jin, \u201cBi-fidelity evolutionary multiobjective search for adversarially robust deep neural architectures,\u201d Neurocomputing, vol. 550, p. 126465, 2023\/09\/14\/2023, doi: https:\/\/doi.org\/10.1016\/j.neucom.2023.126465.","DOI":"10.1016\/j.neucom.2023.126465"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_023","doi-asserted-by":"crossref","unstructured":"S. Wang, Z. Liu, J. Li, M. Gong, and R. Yang, \u201cEvolutionary Multitasking Collaborative Neural Architecture Search for Scene Classification,\u201d in 2024 IEEE Congress on Evolutionary Computation (CEC), 30 June-5 July 2024 2024, pp. 1-8, doi: 10.1109\/CEC60901.2024.10612042.","DOI":"10.1109\/CEC60901.2024.10612042"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_024","doi-asserted-by":"crossref","unstructured":"Y. Gao et al., \u201cHGNAS++: Efficient Architecture Search for Heterogeneous Graph Neural Networks,\u201d IEEE Transactions on Knowledge and Data Engineering, vol. 35, no. 9, pp. 9448-9461, 2023, doi: 10.1109\/TKDE.2023.3239842.","DOI":"10.1109\/TKDE.2023.3239842"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_025","unstructured":"H. Wang, C. Ge, H. Chen, and X. Sun, \u201cPre-NAS: Preferred One-Shot Learning Towards Efficient Neural Architecture Search,\u201d presented at the Proceedings of the 40th International Conference on Machine Learning, Proceedings of Machine Learning Research, [Online]. Available: https:\/\/proceedings.mlr.press\/v202\/wang23f.html, 2023."},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_026","doi-asserted-by":"crossref","unstructured":"L. Ma, H. Kang, G. Yu, Q. Li, and Q. He, \u201cSingle-Domain Generalized Predictor for Neural Architecture Search System,\u201d IEEE Transactions on Computers, vol. 73, no. 5, pp. 1400-1413, 2024, doi: 10.1109\/TC.2024.3365949.","DOI":"10.1109\/TC.2024.3365949"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_027","doi-asserted-by":"crossref","unstructured":"L. P. Kaelbling, M. L. Littman, and A. W. Moore, \u201cReinforcement learning: A survey,\u201d Journal of artificial intelligence research, vol. 4, pp. 237-285, 1996.","DOI":"10.1613\/jair.301"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_028","unstructured":"B. Baker, O. Gupta, N. Naik, and R. Raskar, \u201cDesigning Neural Network Architectures using Reinforcement Learning,\u201d in International Conference on Learning Representations, 2022."},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_029","unstructured":"R. Negrinho and G. Gordon, \u201cDeeparchitect: Automatically designing and training deep architectures,\u201d arXiv preprint arXiv:1704.08792, 2017."},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_030","doi-asserted-by":"crossref","unstructured":"L. Kocsis and C. Szepesv\u00e1ri, \u201cBandit based monte-carlo planning,\u201d in European conference on machine learning, Springer, pp. 282-293, 2006.","DOI":"10.1007\/11871842_29"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_031","doi-asserted-by":"crossref","unstructured":"B. Lyu, S. Wen, K. Shi, and T. Huang, \u201cMultiobjective reinforcement learning-based neural architecture search for efficient portrait parsing,\u201d IEEE Transactions on Cybernetics, vol. 53, no. 2, pp. 1158-1169, 2021.","DOI":"10.1109\/TCYB.2021.3104866"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_032","unstructured":"S. Xie, H. Zheng, C. Liu, and L. Lin, \u201cSNAS: stochastic neural architecture search,\u201d arXiv preprint arXiv:1812.09926, 2018."},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_033","unstructured":"H. Cai, L. Zhu, and S. Han, \u201cProxylessnas: Direct neural architecture search on target task and hardware,\u201d arXiv preprint arXiv:1812.00332, 2018."},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_034","unstructured":"Y. Xu et al., \u201cPc-darts: Partial channel connections for memory-efficient architecture search,\u201d arXiv preprint arXiv:1907.05737, 2019."},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_035","unstructured":"R. S. Sukthanker, A. Krishnakumar, M. Safari, and F. Hutter, \u201cWeight-entanglement meets gradient-based neural architecture search,\u201d arXiv preprint arXiv:2312.10440, 2023."},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_036","unstructured":"L. Xie et al., \u201cZO-DARTS++: An Efficient and Size-Variable Zeroth-Order Neural Architecture Search Algorithm,\u201d arXiv preprint arXiv:2503.06092, 2025."},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_037","doi-asserted-by":"crossref","unstructured":"Y. Wang et al., \u201cMedNAS: Multiscale Training-Free Neural Architecture Search for Medical Image Analysis,\u201d IEEE Transactions on Evolutionary Computation, vol. 28, no. 3, pp. 668-681, 2024, doi: 10.1109\/TEVC.2024.3352641.","DOI":"10.1109\/TEVC.2024.3352641"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_038","unstructured":"Z. Fan, J. Wei, G. Zhu, J. Mo, and W. Li, \u201cEvolutionary neural architecture search for retinal vessel segmentation,\u201d arXiv preprint arXiv:2001.06678, 2020."},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_039","doi-asserted-by":"crossref","unstructured":"Y. Liu, Y. Sun, B. Xue, M. Zhang, G. G. Yen, and K. C. Tan, \u201cA survey on evolutionary neural architecture search,\u201d IEEE transactions on neural networks and learning systems, vol. 34, no. 2, pp. 550-570, 2021.","DOI":"10.1109\/TNNLS.2021.3100554"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_040","doi-asserted-by":"crossref","unstructured":"M. Suganuma, M. Kobayashi, S. Shirakawa, and T. Nagao, \u201cEvolution of deep convolutional neural networks using cartesian genetic programming,\u201d Evolutionary computation, vol. 28, no. 1, pp. 141-163, 2020.","DOI":"10.1162\/evco_a_00253"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_041","doi-asserted-by":"crossref","unstructured":"S. Jiang, Z. Ji, G. Zhu, C. Yuan, and Y. Huang, \u201cOperation-level early stopping for robustifying differentiable NAS,\u201d Advances in Neural Information Processing Systems, vol. 36, pp. 70983-71007, 2023.","DOI":"10.52202\/075280-3109"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_042","doi-asserted-by":"crossref","unstructured":"K. Sakamoto, H. Ishibashi, R. Sato, S. Shirakawa, Y. Akimoto, and H. Hino, \u201cAtnas: Automatic termination for neural architecture search,\u201d Neural Networks, vol. 166, pp. 446-458, 2023.","DOI":"10.1016\/j.neunet.2023.07.011"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_043","doi-asserted-by":"crossref","unstructured":"I. Trofimov, N. Klyuchnikov, M. Salnikov, A. Filippov, and E. Burnaev, \u201cMulti-Fidelity Neural Architecture Search With Knowledge Distillation,\u201d IEEE Access, vol. 11, pp. 59217-59225, 2023, doi: 10.1109\/ACCESS.2023.3234810.","DOI":"10.1109\/ACCESS.2023.3234810"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_044","doi-asserted-by":"crossref","unstructured":"J. Sun, W. Yao, T. Jiang, and X. Chen, \u201cEfficient search of comprehensively robust neural architectures via multi-fidelity evaluation,\u201d Pattern Recognition, vol. 146, p. 110038, 2024\/02\/01\/2024, doi: https:\/\/doi.org\/10.1016\/j.patcog.2023.110038.","DOI":"10.1016\/j.patcog.2023.110038"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_045","doi-asserted-by":"crossref","unstructured":"J. Liu, J. Yan, H. Xu, Z. Wang, J. Huang, and Y. Xu, \u201cFinch: Enhancing Federated Learning With Hierarchical Neural Architecture Search,\u201d IEEE Transactions on Mobile Computing, vol. 23, no. 5, pp. 6012-6026, 2024, doi: 10.1109\/TMC.2023.3315451.","DOI":"10.1109\/TMC.2023.3315451"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_046","doi-asserted-by":"crossref","unstructured":"W. Wang, X. Zhang, H. Cui, H. Yin, and Y. Zhang, \u201cFP-DARTS: Fast parallel differentiable neural architecture search for image classification,\u201d Pattern Recognition, vol. 136, p. 109193, 2023\/04\/01\/2023, doi: https:\/\/doi.org\/10.1016\/j.patcog.2022.109193.","DOI":"10.1016\/j.patcog.2022.109193"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_047","doi-asserted-by":"crossref","unstructured":"Z. Chen, G. Qiu, P. Li, L. Zhu, X. Yang, and B. Sheng, \u201cMNGNAS: Distilling Adaptive Combination of Multiple Searched Networks for One-Shot Neural Architecture Search,\u201d IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 11, pp. 13489-13508, 2023, doi: 10.1109\/TPAMI.2023.3293885.","DOI":"10.1109\/TPAMI.2023.3293885"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_048","doi-asserted-by":"crossref","unstructured":"T. Zhang et al., \u201cNASRec: Weight Sharing Neural Architecture Search for Recommender Systems,\u201d presented at the Proceedings of the ACM Web Conference 2023, Austin, TX, USA, 2023. [Online]. Available: https:\/\/doi.org\/10.1145\/3543507.3583446.","DOI":"10.1145\/3543507.3583446"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_049","doi-asserted-by":"crossref","unstructured":"C. Peng, Y. Li, R. Shang, and L. Jiao, \u201cRSBNet: One-shot neural architecture search for a backbone network in remote sensing image recognition,\u201d Neurocomputing, vol. 537, pp. 110-127, 2023\/06\/07\/2023, doi: https:\/\/doi.org\/10.1016\/j.neucom.2023.03.046.","DOI":"10.1016\/j.neucom.2023.03.046"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_050","unstructured":"A. Krizhevsky and G. Hinton, \u201cLearning multiple layers of features from tiny images,\u201d 2009."},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_051","unstructured":"S. Zagoruyko, \u201cWide residual networks,\u201d arXiv preprint arXiv:1605.07146, 2016."},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_052","doi-asserted-by":"crossref","unstructured":"C. Szegedy et al., \u201cGoing deeper with convolutions,\u201d in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1-9, 2015.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_053","doi-asserted-by":"crossref","unstructured":"X. Zhang, X. Zhou, M. Lin, and J. Sun, \u201cShufflenet: An extremely efficient convolutional neural network for mobile devices,\u201d in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 6848-6856, 2018.","DOI":"10.1109\/CVPR.2018.00716"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_054","doi-asserted-by":"crossref","unstructured":"Z. Zhong, J. Yan, W. Wu, J. Shao, and C.-L. Liu, \u201cPractical block-wise neural network architecture generation,\u201d in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2423-2432, 2018.","DOI":"10.1109\/CVPR.2018.00257"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_055","unstructured":"H. Pham, M. Guan, B. Zoph, Q. Le, and J. Dean, \u201cEfficient neural architecture search via parameters sharing,\u201d in International conference on machine learning, PMLR, pp. 4095-4104, 2018."},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_056","doi-asserted-by":"crossref","unstructured":"H. Cai, T. Chen, W. Zhang, Y. Yu, and J. Wang, \u201cEfficient architecture search by network transformation,\u201d in Proceedings of the AAAI conference on artificial intelligence, vol. 32, no. 1, 2018.","DOI":"10.1609\/aaai.v32i1.11709"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_057","unstructured":"H. Liu, K. Simonyan, and Y. Yang, \u201cDarts: Differentiable architecture search,\u201d arXiv preprint arXiv:1806.09055, 2018."},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_058","unstructured":"R. Luo, F. Tian, T. Qin, E. Chen, and T.-Y. Liu, \u201cNeural architecture optimization,\u201d Advances in neural information processing systems, vol. 31, 2018."},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_059","doi-asserted-by":"crossref","unstructured":"J.-D. Dong, A.-C. Cheng, D.-C. Juan, W. Wei, and M. Sun, \u201cDpp-net: Device-aware progressive search for pareto-optimal neural architectures,\u201d in Proceedings of the European conference on computer vision (ECCV), pp. 517-531, 2018.","DOI":"10.1007\/978-3-030-01252-6_32"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_060","doi-asserted-by":"crossref","unstructured":"G. Biju and G. Pillai, \u201cSequential node search for faster neural architecture search,\u201d Knowledge-Based Systems, vol. 300, p. 112145, 2024.","DOI":"10.1016\/j.knosys.2024.112145"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_061","doi-asserted-by":"crossref","unstructured":"B. Ma, J. Zhang, Y. Xia, and D. Tao, \u201cVNAS: variational neural architecture search,\u201d International Journal of Computer Vision, vol. 132, no. 9, pp. 3689-3713, 2024.","DOI":"10.1007\/s11263-024-02014-w"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_062","doi-asserted-by":"crossref","unstructured":"K. Jing, L. Chen, and J. Xu, \u201cAn architecture entropy regularizer for differentiable neural architecture search,\u201d Neural Networks, vol. 158, pp. 111-120, 2023.","DOI":"10.1016\/j.neunet.2022.11.015"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_063","doi-asserted-by":"crossref","unstructured":"E. Real, A. Aggarwal, Y. Huang, and Q. V. Le, \u201cRegularized evolution for image classifier architecture search,\u201d in Proceedings of the aaai conference on artificial intelligence, vol. 33, no. 01, pp. 4780-4789, 2019.","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_064","unstructured":"H. Liu, K. Simonyan, O. Vinyals, C. Fernando, and K. Kavukcuoglu, \u201cHierarchical representations for efficient architecture search,\u201d arXiv preprint arXiv:1711.00436, 2017."},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_065","unstructured":"E. Real et al., \u201cLarge-scale evolution of image classifiers,\u201d in International conference on machine learning, PMLR, pp. 2902-2911, 2017."},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_066","doi-asserted-by":"crossref","unstructured":"Y. Sun, B. Xue, M. Zhang, G. G. Yen, and J. Lv, \u201cAutomatically designing CNN architectures using the genetic algorithm for image classification,\u201d IEEE transactions on cybernetics, vol. 50, no. 9, pp. 3840-3854, 2020.","DOI":"10.1109\/TCYB.2020.2983860"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_067","doi-asserted-by":"crossref","unstructured":"L. Xie and A. Yuille, \u201cGenetic cnn,\u201d in Proceedings of the IEEE international conference on computer vision, pp. 1379-1388, 2017.","DOI":"10.1109\/ICCV.2017.154"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_068","doi-asserted-by":"crossref","unstructured":"Z. Lu et al., \u201cNSGA-Net: Neural architecture search using multi-objective genetic algorithm,\u201d in Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, pp. 4750-4754, 2021.","DOI":"10.24963\/ijcai.2020\/659"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_069","doi-asserted-by":"crossref","unstructured":"Y. Sun, H. Wang, B. Xue, Y. Jin, G. G. Yen, and M. Zhang, \u201cSurrogate-Assisted Evolutionary Deep Learning Using an End-to-End Random Forest-Based Performance Predictor,\u201d IEEE Transactions on Evolutionary Computation, vol. 24, no. 2, 2020.","DOI":"10.1109\/TEVC.2019.2924461"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_070","doi-asserted-by":"crossref","unstructured":"Y. Sun, B. Xue, M. Zhang, and G. G. Yen, \u201cCompletely Automated CNN Architecture Design Based on Blocks,\u201d IEEE transactions on neural networks and learning systems, vol. 31, no. 4, pp. 1242-1254, 2020.","DOI":"10.1109\/TNNLS.2019.2919608"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_071","doi-asserted-by":"crossref","unstructured":"C. He, H. Tan, S. Huang, and R. Cheng, \u201cEfficient evolutionary neural architecture search by modular inheritable crossover,\u201d Swarm and Evolutionary Computation, vol. 64, p. 100894, 2021.","DOI":"10.1016\/j.swevo.2021.100894"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_072","unstructured":"H. Zhang, Y. Jin, R. Cheng, and K. Hao, \u201cSampled training and node inheritance for fast evolutionary neural architecture search,\u201d arXiv preprint arXiv:2003.11613, 2020."},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_073","doi-asserted-by":"crossref","unstructured":"Z. Yang et al., \u201cCars: Continuous evolution for efficient neural architecture search,\u201d in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 1829-1838, 2020.","DOI":"10.1109\/CVPR42600.2020.00190"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_074","doi-asserted-by":"crossref","unstructured":"T. Elsken, J. H. Metzen, and F. Hutter, \u201cEfficient multi-objective neural architecture search via lamarckian evolution,\u201d arXiv preprint arXiv:1804.09081, 2018.","DOI":"10.1007\/978-3-030-05318-5_11"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_075","doi-asserted-by":"crossref","unstructured":"Y. Xue, X. Han, F. Neri, J. Qin, and D. Pelusi, \u201cA gradient-guided evolutionary neural architecture search,\u201d IEEE transactions on neural networks and learning systems, 2024.","DOI":"10.1109\/TNNLS.2024.3371432"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_076","doi-asserted-by":"crossref","unstructured":"Y. Xue, C. Chen, and A. S\u0142owik, \u201cNeural architecture search based on a multi-objective evolutionary algorithm with probability stack,\u201d IEEE Transactions on Evolutionary Computation, vol. 27, no. 4, pp. 778-786, 2023.","DOI":"10.1109\/TEVC.2023.3252612"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_077","doi-asserted-by":"crossref","unstructured":"Y. Tian, S. Peng, S. Yang, X. Zhang, K. C. Tan, and Y. Jin, \u201cAction Command Encoding for Surrogate-Assisted Neural Architecture Search,\u201d IEEE Transactions on Cognitive and Developmental Systems, vol. 14, no. 3, 2022.","DOI":"10.1109\/TCDS.2021.3107555"},{"key":"2026042812092652618_j_jaiscr-2025-0020_ref_078","doi-asserted-by":"crossref","unstructured":"X. Zheng et al., \u201cDdpnas: Efficient neural architecture search via dynamic distribution pruning,\u201d International Journal of Computer Vision, vol. 131, no. 5, pp. 1234-1249, 2023.","DOI":"10.1007\/s11263-023-01753-6"}],"container-title":["Journal of Artificial Intelligence and Soft Computing Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/reference-global.com\/pdf\/10.2478\/jaiscr-2025-0020","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T19:07:35Z","timestamp":1777403255000},"score":1,"resource":{"primary":{"URL":"https:\/\/reference-global.com\/article\/10.2478\/jaiscr-2025-0020"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,11]]},"references-count":78,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,7,11]]},"published-print":{"date-parts":[[2025,10,1]]}},"alternative-id":["10.2478\/jaiscr-2025-0020"],"URL":"https:\/\/doi.org\/10.2478\/jaiscr-2025-0020","relation":{},"ISSN":["2449-6499"],"issn-type":[{"value":"2449-6499","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,11]]}}}