{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T02:31:51Z","timestamp":1779935511642,"version":"3.53.1"},"reference-count":147,"publisher":"Elsevier BV","issue":"1","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2023,11,3]],"date-time":"2023-11-03T00:00:00Z","timestamp":1698969600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100020595","name":"National Science and Technology Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100020595","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["ICT Express"],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1016\/j.icte.2023.11.001","type":"journal-article","created":{"date-parts":[[2023,11,10]],"date-time":"2023-11-10T01:07:15Z","timestamp":1699578435000},"page":"213-231","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":22,"title":["Training-free neural architecture search: A review"],"prefix":"10.1016","volume":"10","author":[{"given":"Meng-Ting","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0128-4052","authenticated-orcid":false,"given":"Chun-Wei","family":"Tsai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"3","key":"10.1016\/j.icte.2023.11.001_b1","doi-asserted-by":"crossref","first-page":"2224","DOI":"10.1109\/COMST.2019.2904897","article-title":"Deep learning in mobile and wireless networking: A survey","volume":"21","author":"Zhang","year":"2019","journal-title":"IEEE Commun. Surv. Tutor."},{"issue":"4","key":"10.1016\/j.icte.2023.11.001_b2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3329784","article-title":"Understanding deep learning techniques for image segmentation","volume":"52","author":"Ghosh","year":"2019","journal-title":"ACM Comput. Surv."},{"issue":"1","key":"10.1016\/j.icte.2023.11.001_b3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3158369","article-title":"Deep learning based recommender system: A survey and new perspectives","volume":"52","author":"Zhang","year":"2019","journal-title":"ACM Comput. Surv."},{"issue":"5","key":"10.1016\/j.icte.2023.11.001_b4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3234150","article-title":"A survey on deep learning: Algorithms, techniques, and applications","volume":"51","author":"Pouyanfar","year":"2018","journal-title":"ACM Comput. Surv."},{"issue":"11","key":"10.1016\/j.icte.2023.11.001_b5","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"Lecun","year":"1998","journal-title":"Proc. IEEE"},{"issue":"6","key":"10.1016\/j.icte.2023.11.001_b6","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"ImageNet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun. ACM"},{"key":"10.1016\/j.icte.2023.11.001_b7","series-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"issue":"4","key":"10.1016\/j.icte.2023.11.001_b8","doi-asserted-by":"crossref","first-page":"1595","DOI":"10.1016\/j.jksuci.2021.11.019","article-title":"A review on TinyML: State-of-the-art and prospects","volume":"34","author":"Ray","year":"2022","journal-title":"J. King Saud Univ. - Comput. Inf. Sci."},{"issue":"4","key":"10.1016\/j.icte.2023.11.001_b9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3398209","article-title":"Deep learning on mobile and embedded devices: State-of-the-art, challenges, and future directions","volume":"53","author":"Chen","year":"2020","journal-title":"ACM Comput. Surv."},{"issue":"18","key":"10.1016\/j.icte.2023.11.001_b10","doi-asserted-by":"crossref","first-page":"13849","DOI":"10.1109\/JIOT.2021.3088875","article-title":"A survey of recent advances in edge-computing-powered artificial intelligence of things","volume":"8","author":"Chang","year":"2021","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.icte.2023.11.001_b11","article-title":"TinyML meets IoT: A comprehensive survey","volume":"16","author":"Dutta","year":"2021","journal-title":"Int. Things"},{"key":"10.1016\/j.icte.2023.11.001_b12","series-title":"TinyML for ubiquitous edge AI","author":"Soro","year":"2021"},{"issue":"3","key":"10.1016\/j.icte.2023.11.001_b13","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/MCAS.2020.3005467","article-title":"TinyML-enabled frugal smart objects: Challenges and opportunities","volume":"20","author":"Sanchez-Iborra","year":"2020","journal-title":"IEEE Circuits Syst. Mag."},{"key":"10.1016\/j.icte.2023.11.001_b14","doi-asserted-by":"crossref","first-page":"370","DOI":"10.1016\/j.neucom.2021.07.045","article-title":"Pruning and quantization for deep neural network acceleration: A survey","volume":"461","author":"Liang","year":"2021","journal-title":"Neurocomputing"},{"issue":"4","key":"10.1016\/j.icte.2023.11.001_b15","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1109\/JPROC.2020.2976475","article-title":"Model compression and hardware acceleration for neural networks: A comprehensive survey","volume":"108","author":"Deng","year":"2020","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.icte.2023.11.001_b16","series-title":"Taking human out of learning applications: A survey on automated machine learning","author":"Yao","year":"2018"},{"key":"10.1016\/j.icte.2023.11.001_b17","doi-asserted-by":"crossref","unstructured":"S. Fong, S. Deb, X.-S. Yang, How meta-heuristic algorithms contribute to deep learning in the hype of big data analytics, in: Proceedings of the Progress in Intelligent Computing Techniques: Theory, Practice, and Applications, Vol. 518, 2018, pp. 3\u201325.","DOI":"10.1007\/978-981-10-3373-5_1"},{"key":"10.1016\/j.icte.2023.11.001_b18","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2020.106622","article-title":"AutoML: A survey of the state-of-the-art","volume":"212","author":"He","year":"2021","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.icte.2023.11.001_b19","doi-asserted-by":"crossref","DOI":"10.1016\/j.phycom.2020.101057","article-title":"Novel suboptimal approaches for hyperparameter tuning of deep neural network [under the shelf of optical communication]","volume":"41","author":"Amirabadi","year":"2020","journal-title":"Phys. Commun."},{"issue":"4","key":"10.1016\/j.icte.2023.11.001_b20","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3447582","article-title":"A comprehensive survey of neural architecture search: Challenges and solutions","volume":"54","author":"Ren","year":"2021","journal-title":"ACM Comput. Surv."},{"issue":"1","key":"10.1016\/j.icte.2023.11.001_b21","first-page":"1997","article-title":"Neural architecture search: A survey","volume":"20","author":"Elsken","year":"2019","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"10.1016\/j.icte.2023.11.001_b22","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1109\/JSYST.2013.2256731","article-title":"Metaheuristic scheduling for cloud: A survey","volume":"8","author":"Tsai","year":"2014","journal-title":"IEEE Syst. J."},{"key":"10.1016\/j.icte.2023.11.001_b23","doi-asserted-by":"crossref","unstructured":"C. Liu, L.-C. Chen, F. Schroff, H. Adam, W. Hua, A.L. Yuille, L. Fei-Fei, Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 82\u201392.","DOI":"10.1109\/CVPR.2019.00017"},{"key":"10.1016\/j.icte.2023.11.001_b24","doi-asserted-by":"crossref","unstructured":"N. Wang, Y. Gao, H. Chen, P. Wang, Z. Tian, C. Shen, Y. Zhang, NAS-FCOS: Fast Neural Architecture Search for Object Detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 11943\u201311951.","DOI":"10.1109\/CVPR42600.2020.01196"},{"key":"10.1016\/j.icte.2023.11.001_b25","unstructured":"Y. Gou, B. Li, Z. Liu, S. Yang, X. Peng, CLEARER: Multi-Scale Neural Architecture Search for Image Restoration, in: Proceedings of the Advances in Neural Information Processing Systems, Vol. 33, 2020, pp. 17129\u201317140."},{"key":"10.1016\/j.icte.2023.11.001_b26","series-title":"Autospeech: Neural architecture search for speaker recognition","author":"Ding","year":"2020"},{"issue":"6","key":"10.1016\/j.icte.2023.11.001_b27","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"Imagenet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun. ACM"},{"key":"10.1016\/j.icte.2023.11.001_b28","series-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"10.1016\/j.icte.2023.11.001_b29","doi-asserted-by":"crossref","unstructured":"C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, A. Rabinovich, Going deeper with convolutions, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 1\u20139.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"10.1016\/j.icte.2023.11.001_b30","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.icte.2023.11.001_b31","series-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and\u00a1 0.5 MB model size","author":"Iandola","year":"2016"},{"key":"10.1016\/j.icte.2023.11.001_b32","series-title":"Neural architecture search with reinforcement learning","author":"Zoph","year":"2016"},{"key":"10.1016\/j.icte.2023.11.001_b33","doi-asserted-by":"crossref","unstructured":"E. Real, A. Aggarwal, Y. Huang, Q.V. Le, Regularized evolution for image classifier architecture search, in: Proceedings of the AAAI Conference on Artificial Intelligence, 2019, pp. 4780\u20134789.","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"10.1016\/j.icte.2023.11.001_b34","doi-asserted-by":"crossref","unstructured":"B. Zoph, V. Vasudevan, J. Shlens, Q.V. Le, Learning Transferable Architectures for Scalable Image Recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2018, pp. 8697\u20138710.","DOI":"10.1109\/CVPR.2018.00907"},{"key":"10.1016\/j.icte.2023.11.001_b35","series-title":"Accelerating neural architecture search via proxy data","author":"Na","year":"2021"},{"issue":"01","key":"10.1016\/j.icte.2023.11.001_b36","first-page":"4780","article-title":"Regularized evolution for image classifier architecture search","volume":"33","author":"Real","year":"2019","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.icte.2023.11.001_b37","series-title":"A downsampled variant of imagenet as an alternative to the cifar datasets","author":"Chrabaszcz","year":"2017"},{"key":"10.1016\/j.icte.2023.11.001_b38","doi-asserted-by":"crossref","unstructured":"J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, L. Fei-Fei, ImageNet: A large-scale hierarchical image database, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2009, pp. 248\u2013255.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"10.1016\/j.icte.2023.11.001_b39","unstructured":"T. Domhan, J.T. Springenberg, F. Hutter, Speeding up automatic hyperparameter optimization of deep neural networks by extrapolation of learning curves, in: Proceedings of the International Joint Conference on Artificial Intelligence, 2015, pp. 3460\u20133468."},{"key":"10.1016\/j.icte.2023.11.001_b40","unstructured":"A. Klein, S. Falkner, J.T. Springenberg, F. Hutter, Learning curve prediction with Bayesian neural networks, in: Proceedings of the International Conference on Learning Representations, 2017."},{"key":"10.1016\/j.icte.2023.11.001_b41","series-title":"Accelerating neural architecture search using performance prediction","author":"Baker","year":"2017"},{"key":"10.1016\/j.icte.2023.11.001_b42","doi-asserted-by":"crossref","unstructured":"C. Liu, B. Zoph, M. Neumann, J. Shlens, W. Hua, L.-J. Li, L. Fei-Fei, A. Yuille, J. Huang, K. Murphy, Progressive neural architecture search, in: Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 19\u201334.","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"10.1016\/j.icte.2023.11.001_b43","series-title":"Net2net: Accelerating learning via knowledge transfer","author":"Chen","year":"2015"},{"issue":"1","key":"10.1016\/j.icte.2023.11.001_b44","first-page":"2787","article-title":"Efficient architecture search by network transformation","volume":"32","author":"Cai","year":"2018","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.icte.2023.11.001_b45","series-title":"Simple and efficient architecture search for convolutional neural networks","author":"Elsken","year":"2017"},{"key":"10.1016\/j.icte.2023.11.001_b46","unstructured":"H. Pham, M. Guan, B. Zoph, Q. Le, J. Dean, Efficient neural architecture search via parameters sharing, in: Proceedings of the International Conference on Machine Learning, 2018, pp. 4095\u20134104."},{"key":"10.1016\/j.icte.2023.11.001_b47","series-title":"International Conference on Learning Representations","article-title":"DARTS: Differentiable architecture search","author":"Liu","year":"2019"},{"key":"10.1016\/j.icte.2023.11.001_b48","series-title":"Neural architecture search: Insights from 1000 papers","author":"White","year":"2023"},{"key":"10.1016\/j.icte.2023.11.001_b49","series-title":"Efficient evaluation methods for neural architecture search: A survey","author":"Xie","year":"2023"},{"key":"10.1016\/j.icte.2023.11.001_b50","unstructured":"J. Mellor, J. Turner, A. Storkey, E.J. Crowley, Neural architecture search without training, in: Proceedings of the International Conference on Machine Learning, 2021, pp. 7588\u20137598."},{"key":"10.1016\/j.icte.2023.11.001_b51","unstructured":"M. Javaheripi, S. Shah, S. Mukherjee, T.L. Religa, C.C.T. Mendes, G.H. de\u00a0Rosa, S. Bubeck, F. Koushanfar, D. Dey, LiteTransformerSearch: Training-free On-device Search for Efficient Autoregressive Language Models, in: Proceedings of the Conference on Automated Machine Learning, 2022."},{"key":"10.1016\/j.icte.2023.11.001_b52","doi-asserted-by":"crossref","unstructured":"M.-T. Wu, H.-I. Lin, C.-W. Tsai, A Training-free Genetic Neural Architecture Search, in: Proceedings of the ACM International Conference on Intelligent Computing and Its Emerging Applications, 2021, pp. 65\u201370.","DOI":"10.1145\/3491396.3506510"},{"key":"10.1016\/j.icte.2023.11.001_b53","unstructured":"M.S. Abdelfattah, A. Mehrotra, \u0141. Dudziak, N.D. Lane, Zero-cost proxies for lightweight NAS, in: Proceedings of the International Conference on Learning Representations, 2021."},{"key":"10.1016\/j.icte.2023.11.001_b54","series-title":"Zero-cost proxies meet differentiable architecture search","author":"Xiang","year":"2021"},{"key":"10.1016\/j.icte.2023.11.001_b55","doi-asserted-by":"crossref","unstructured":"N. Cavagnero, L. Robbiano, B. Caputo, G. Averta, FreeREA: Training-Free Evolution-based Architecture Search, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2023, pp. 1493\u20131502.","DOI":"10.1109\/WACV56688.2023.00154"},{"key":"10.1016\/j.icte.2023.11.001_b56","doi-asserted-by":"crossref","unstructured":"N. Mokhtari, A. N\u00e9d\u00e9lec, M. Gilles, P. De\u00a0Loor, Improving Neural Architecture Search by Mixing a FireFly algorithm with a Training Free Evaluation, in: Proceedings of the International Joint Conference on Neural Networks, 2022, pp. 1\u20138.","DOI":"10.1109\/IJCNN55064.2022.9892861"},{"key":"10.1016\/j.icte.2023.11.001_b57","unstructured":"Z. Zhang, Z. Jia, GradSign: Model Performance Inference with Theoretical Insights, in: Proceedings of the International Conference on Learning Representations, 2022."},{"key":"10.1016\/j.icte.2023.11.001_b58","unstructured":"C. White, M. Khodak, R. Tu, S. Shah, S. Bubeck, D. Dey, A deeper look at zero-cost proxies for lightweight NAS, https:\/\/iclr-blog-track.github.io\/2022\/03\/25\/zero-cost-proxies\/."},{"key":"10.1016\/j.icte.2023.11.001_b59","series-title":"Low-cost recurrent neural network expected performance evaluation","author":"Camero","year":"2018"},{"key":"10.1016\/j.icte.2023.11.001_b60","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2021.107356","article-title":"Bayesian neural architecture search using a training-free performance metric","volume":"106","author":"Camero","year":"2021","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.icte.2023.11.001_b61","series-title":"Reliable and fast recurrent neural network architecture optimization","author":"Camero","year":"2021"},{"key":"10.1016\/j.icte.2023.11.001_b62","doi-asserted-by":"crossref","unstructured":"V. Lopes, S. Alirezazadeh, L.A. Alexandre, EPE-NAS: Efficient performance estimation without training for neural architecture search, in: Proceedings of the International Conference on Artificial Neural Networks, 2021, pp. 552\u2013563.","DOI":"10.1007\/978-3-030-86383-8_44"},{"key":"10.1016\/j.icte.2023.11.001_b63","series-title":"Neural architecture search on imagenet in four GPU hours: A theoretically inspired perspective","author":"Chen","year":"2021"},{"key":"10.1016\/j.icte.2023.11.001_b64","doi-asserted-by":"crossref","unstructured":"T. Do, N.H. Luong, Training-free multi-objective evolutionary neural architecture search via neural tangent kernel and number of linear regions, in: Proceedings of the International Conference on Neural Information Processing, 2021, pp. 335\u2013347.","DOI":"10.1007\/978-3-030-92270-2_29"},{"key":"10.1016\/j.icte.2023.11.001_b65","unstructured":"B. Hanin, D. Rolnick, Complexity of linear regions in deep networks, in: Proceedings of the International Conference on Machine Learning, 2019, pp. 2596\u20132604."},{"key":"10.1016\/j.icte.2023.11.001_b66","doi-asserted-by":"crossref","unstructured":"M. Lin, P. Wang, Z. Sun, H. Chen, X. Sun, Q. Qian, H. Li, R. Jin, Zen-NAS: A zero-shot NAS for high-performance image recognition, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 347\u2013356.","DOI":"10.1109\/ICCV48922.2021.00040"},{"key":"10.1016\/j.icte.2023.11.001_b67","unstructured":"Z. Sun, M. Lin, X. Sun, Z. Tan, H. Li, R. Jin, MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection, in: Proceedings of the International Conference on Machine Learning, 2022, pp. 20810\u201320826."},{"key":"10.1016\/j.icte.2023.11.001_b68","series-title":"Auto-scaling vision transformers without training","author":"Chen","year":"2022"},{"key":"10.1016\/j.icte.2023.11.001_b69","series-title":"Faster gaze prediction with dense networks and fisher pruning","author":"Theis","year":"2018"},{"key":"10.1016\/j.icte.2023.11.001_b70","series-title":"BlockSwap: Fisher-guided block substitution for network compression on a budget","author":"Turner","year":"2019"},{"key":"10.1016\/j.icte.2023.11.001_b71","series-title":"SNIP: Single-shot network pruning based on connection sensitivity","author":"Lee","year":"2018"},{"key":"10.1016\/j.icte.2023.11.001_b72","series-title":"Picking winning tickets before training by preserving gradient flow","author":"Wang","year":"2020"},{"key":"10.1016\/j.icte.2023.11.001_b73","unstructured":"H. Tanaka, D. Kunin, D.L. Yamins, S. Ganguli, Pruning neural networks without any data by iteratively conserving synaptic flow 33 (2020) 6377\u20136389."},{"key":"10.1016\/j.icte.2023.11.001_b74","series-title":"Deep neural networks as gaussian processes","author":"Lee","year":"2017"},{"key":"10.1016\/j.icte.2023.11.001_b75","series-title":"Towards nngp-guided neural architecture search","author":"Park","year":"2020"},{"key":"10.1016\/j.icte.2023.11.001_b76","unstructured":"A. Jacot, F. Gabriel, C. Hongler, Neural tangent kernel: Convergence and generalization in neural networks, in: Proceedings of the Conference on Neural Information Processing Systems, Vol. 31, 2018, pp. 8580\u20138589."},{"key":"10.1016\/j.icte.2023.11.001_b77","doi-asserted-by":"crossref","unstructured":"H. Wang, Y. Wang, R. Sun, B. Li, Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 9797\u20139808.","DOI":"10.1109\/CVPR52688.2022.00957"},{"key":"10.1016\/j.icte.2023.11.001_b78","unstructured":"Y. Shu, S. Cai, Z. Dai, B.C. Ooi, B.K.H. Low, NASI: Label-and Data-agnostic Neural Architecture Search at Initialization, in: Proceedings of the International Conference on Learning Representations, 2022."},{"key":"10.1016\/j.icte.2023.11.001_b79","unstructured":"J. Xu, L. Zhao, J. Lin, R. Gao, X. Sun, H. Yang, KNAS: Green neural architecture search, in: Proceedings of the International Conference on Machine Learning, 2021, pp. 11613\u201311625."},{"key":"10.1016\/j.icte.2023.11.001_b80","first-page":"1","article-title":"A training-free neural architecture search algorithm based on search economics","author":"Wu","year":"2023","journal-title":"IEEE Trans. Evol. Comput."},{"key":"10.1016\/j.icte.2023.11.001_b81","series-title":"Understanding and accelerating neural architecture search with training-free and theory-grounded metrics","author":"Chen","year":"2021"},{"key":"10.1016\/j.icte.2023.11.001_b82","doi-asserted-by":"crossref","first-page":"133914","DOI":"10.1109\/ACCESS.2021.3115911","article-title":"A feature fusion based indicator for training-free neural architecture search","volume":"9","author":"Tran","year":"2021","journal-title":"IEEE Access"},{"key":"10.1016\/j.icte.2023.11.001_b83","series-title":"Handbook of Metaheuristic Algorithms: From Fundamental Theories To Advanced Applications","author":"Tsai","year":"2023"},{"issue":"5","key":"10.1016\/j.icte.2023.11.001_b84","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1016\/0305-0548(86)90048-1","article-title":"Future paths for integer programming and links to artificial intelligence","volume":"13","author":"Glover","year":"1986","journal-title":"Comput. Oper. Res."},{"issue":"3","key":"10.1016\/j.icte.2023.11.001_b85","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1145\/937503.937505","article-title":"Metaheuristics in combinatorial optimization: Overview and conceptual comparison","volume":"35","author":"Blum","year":"2003","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.icte.2023.11.001_b86","series-title":"Handbook of Metaheuristics","year":"2003"},{"issue":"3","key":"10.1016\/j.icte.2023.11.001_b87","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1016\/0167-8191(90)90086-O","article-title":"Genetic algorithms and neural networks: Optimizing connections and connectivity","volume":"14","author":"Whitley","year":"1990","journal-title":"Parallel Comput."},{"key":"10.1016\/j.icte.2023.11.001_b88","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1007\/s13042-010-0004-x","article-title":"Genetic Algorithm-Neural Network (GANN): A study of neural network activation functions and depth of genetic algorithm search applied to feature selection","volume":"1","author":"Tong","year":"2010","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"10.1016\/j.icte.2023.11.001_b89","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1007\/s10462-011-9208-z","article-title":"An optimizing BP neural network algorithm based on genetic algorithm","volume":"36","author":"Ding","year":"2011","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.icte.2023.11.001_b90","series-title":"AutoML: A survey of the state-of-the-art","author":"He","year":"2019"},{"key":"10.1016\/j.icte.2023.11.001_b91","series-title":"Design and Analysis of Experiments By Douglas Montgomery: A Supplement for using JMP","author":"Rushing","year":"2013"},{"key":"10.1016\/j.icte.2023.11.001_b92","unstructured":"J.S. Bergstra, R. Bardenet, Y. Bengio, B. K\u00e9gl, Algorithms for hyper-parameter optimization, in: Proceedings of the International Conference on Neural Information Processing, 2011, pp. 2546\u20132554."},{"key":"10.1016\/j.icte.2023.11.001_b93","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"Bergstra","year":"2012","journal-title":"J. Mach. Learn. Res."},{"issue":"20","key":"10.1016\/j.icte.2023.11.001_b94","first-page":"1","article-title":"Effective hyperparameter optimization using Nelder-Mead method in deep learning","volume":"9","author":"Ozaki","year":"2017","journal-title":"IPSJ Trans. Comput. Vis. Appl."},{"issue":"1","key":"10.1016\/j.icte.2023.11.001_b95","first-page":"26","article-title":"Hyperparameter optimization for machine learning models based on Bayesian optimizationb","volume":"17","author":"Wu","year":"2019","journal-title":"J. Electron. Sci. Technol."},{"key":"10.1016\/j.icte.2023.11.001_b96","doi-asserted-by":"crossref","unstructured":"B. Qolomany, M. Maabreh, A. Al-Fuqaha, A. Gupta, D. Benhaddou, Parameters optimization of deep learning models using particle swarm optimization, in: Proceedings of the International Wireless Communications and Mobile Computing Conference, 2017, pp. 1285\u20131290.","DOI":"10.1109\/IWCMC.2017.7986470"},{"key":"10.1016\/j.icte.2023.11.001_b97","series-title":"Optimization of convolutional neural network using the linearly decreasing weight particle swarm optimization","author":"Serizawa","year":"2020"},{"issue":"55","key":"10.1016\/j.icte.2023.11.001_b98","first-page":"1","article-title":"Neural architecture search: A survey","volume":"20","author":"Elsken","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.icte.2023.11.001_b99","doi-asserted-by":"crossref","unstructured":"M. Lin, R. Ji, Y. Zhang, B. Zhang, Y. Wu, Y. Tian, Channel pruning via automatic structure search, in: Proceedings of the International Joint Conference on Artificial Intelligence, 2020, pp. 673\u2013679.","DOI":"10.24963\/ijcai.2020\/94"},{"issue":"3","key":"10.1016\/j.icte.2023.11.001_b100","doi-asserted-by":"crossref","first-page":"1626","DOI":"10.1109\/TCYB.2019.2928174","article-title":"A knee-guided evolutionary algorithm for compressing deep neural networks","volume":"51","author":"Zhou","year":"2019","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.icte.2023.11.001_b101","doi-asserted-by":"crossref","unstructured":"L. Xie, A. Yuille, Genetic CNN, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 1379\u20131388.","DOI":"10.1109\/ICCV.2017.154"},{"key":"10.1016\/j.icte.2023.11.001_b102","doi-asserted-by":"crossref","unstructured":"P.R. Lorenzo, J. Nalepa, Memetic Evolution of Deep Neural Networks, in: Proceedings of the Genetic and Evolutionary Computation Conference, 2018, pp. 505\u2013512.","DOI":"10.1145\/3205455.3205631"},{"issue":"2","key":"10.1016\/j.icte.2023.11.001_b103","doi-asserted-by":"crossref","first-page":"394","DOI":"10.1109\/TEVC.2019.2916183","article-title":"Evolving deep convolutional neural networks for image classification","volume":"24","author":"Sun","year":"2020","journal-title":"IEEE Trans. Evol. Comput."},{"issue":"4","key":"10.1016\/j.icte.2023.11.001_b104","doi-asserted-by":"crossref","first-page":"1242","DOI":"10.1109\/TNNLS.2019.2919608","article-title":"Completely automated CNN architecture design based on blocks","volume":"31","author":"Sun","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"7","key":"10.1016\/j.icte.2023.11.001_b105","first-page":"855","article-title":"Training-free hardware-aware neural architecture search with reinforcement learning","volume":"26","author":"Tran","year":"2021","journal-title":"J. Broadcast Eng."},{"key":"10.1016\/j.icte.2023.11.001_b106","series-title":"Differentiable architecture search without training nor labels: A pruning perspective","author":"Zhang","year":"2021"},{"key":"10.1016\/j.icte.2023.11.001_b107","doi-asserted-by":"crossref","first-page":"67851","DOI":"10.1109\/ACCESS.2022.3184291","article-title":"IGWO-SS: Improved grey wolf optimization based on synaptic saliency for fast neural architecture search in computer vision","volume":"10","author":"Arman","year":"2022","journal-title":"IEEE Access"},{"key":"10.1016\/j.icte.2023.11.001_b108","doi-asserted-by":"crossref","unstructured":"R. Geada, A.S. McGough, SpiderNet: Hybrid Differentiable-Evolutionary Architecture Search via Train-Free Metrics, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022, pp. 1962\u20131970.","DOI":"10.1109\/CVPRW56347.2022.00213"},{"key":"10.1016\/j.icte.2023.11.001_b109","unstructured":"C. Ying, A. Klein, E. Christiansen, E. Real, K. Murphy, F. Hutter, NAS-Bench-101: Towards reproducible neural architecture search, in: Proceedings of the International Conference on Machine Learning, 2019, pp. 7105\u20137114."},{"key":"10.1016\/j.icte.2023.11.001_b110","unstructured":"X. Dong, Y. Yang, NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search, in: Proceedings of the International Conference on Learning Representations, 2020."},{"issue":"7","key":"10.1016\/j.icte.2023.11.001_b111","first-page":"3634","article-title":"NATS-Bench: Benchmarking NAS algorithms for architecture topology and size","volume":"44","author":"Dong","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.icte.2023.11.001_b112","series-title":"NAS-Bench-301 and the case for surrogate benchmarks for neural architecture search","author":"Siems","year":"2020"},{"key":"10.1016\/j.icte.2023.11.001_b113","series-title":"NAS-Bench-1Shot1: Benchmarking and dissecting one-shot neural architecture search","author":"Zela","year":"2020"},{"key":"10.1016\/j.icte.2023.11.001_b114","doi-asserted-by":"crossref","unstructured":"T. Mikolov, M. Karafi\u00e1t, L. Burget, J. Cernock\u1ef3, S. Khudanpur, Recurrent neural network based language model, in: Proceedings of the Annual Conference of the International Speech Communication Association, Vol. 2, 2010, pp. 1045\u20131048, no. 3.","DOI":"10.21437\/Interspeech.2010-343"},{"key":"10.1016\/j.icte.2023.11.001_b115","series-title":"Pointer sentinel mixture models","author":"Merity","year":"2016"},{"key":"10.1016\/j.icte.2023.11.001_b116","doi-asserted-by":"crossref","first-page":"45736","DOI":"10.1109\/ACCESS.2022.3169897","article-title":"NAS-Bench-NLP: Neural architecture search benchmark for natural language processing","volume":"10","author":"Klyuchnikov","year":"2022","journal-title":"IEEE Access"},{"key":"10.1016\/j.icte.2023.11.001_b117","doi-asserted-by":"crossref","unstructured":"A.R. Zamir, A. Sax, W. Shen, L.J. Guibas, J. Malik, S. Savarese, Taskonomy: Disentangling task transfer learning, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 3712\u20133722.","DOI":"10.1109\/CVPR.2018.00391"},{"key":"10.1016\/j.icte.2023.11.001_b118","doi-asserted-by":"crossref","unstructured":"Y. Duan, X. Chen, H. Xu, Z. Chen, X. Liang, T. Zhang, Z. Li, TransNAS-Bench-101: Improving transferability and generalizability of cross-task neural architecture search, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 5251\u20135260.","DOI":"10.1109\/CVPR46437.2021.00521"},{"key":"10.1016\/j.icte.2023.11.001_b119","doi-asserted-by":"crossref","unstructured":"G.D. Clifford, C. Liu, B. Moody, H.L. Li-wei, I. Silva, Q. Li, A. Johnson, R.G. Mark, AF classification from a short single lead ECG recording: The PhysioNet\/computing in cardiology challenge 2017, in: Proceedings of the Computing in Cardiology, 2017, pp. 1\u20134.","DOI":"10.22489\/CinC.2017.065-469"},{"issue":"5696","key":"10.1016\/j.icte.2023.11.001_b120","doi-asserted-by":"crossref","first-page":"636","DOI":"10.1126\/science.1105136","article-title":"The ENCODE (ENCyclopedia of DNA elements) project","volume":"306","author":"Feingold","year":"2004","journal-title":"Science"},{"key":"10.1016\/j.icte.2023.11.001_b121","series-title":"NAS-Bench-360: Benchmarking diverse tasks for neural architecture search","author":"Tu","year":"2021"},{"key":"10.1016\/j.icte.2023.11.001_b122","series-title":"NAS-bench-zero: A large scale dataset for understanding zero-shot neural architecture search","author":"Chen","year":"2022"},{"key":"10.1016\/j.icte.2023.11.001_b123","series-title":"Learning Multiple Layers of Features from Tiny Images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.icte.2023.11.001_b124","series-title":"Spherical CNNs","author":"Cohen","year":"2018"},{"key":"10.1016\/j.icte.2023.11.001_b125","doi-asserted-by":"crossref","unstructured":"M. Atzori, A. Gijsberts, S. Heynen, A.-G.M. Hager, O. Deriaz, P. Van Der\u00a0Smagt, C. Castellini, B. Caputo, H. M\u00fcller, Building the Ninapro database: A resource for the biorobotics community, in: Proceedings of the IEEE RAS & EMBS International Conference on Biomedical Robotics and Biomechatronics, 2012, pp. 1258\u20131265.","DOI":"10.1109\/BioRob.2012.6290287"},{"issue":"1","key":"10.1016\/j.icte.2023.11.001_b126","doi-asserted-by":"crossref","first-page":"24","DOI":"10.3847\/1538-4357\/ab3fa6","article-title":"deepCR: Cosmic ray rejection with deep learning","volume":"889","author":"Zhang","year":"2020","journal-title":"Astrophys. J."},{"issue":"8","key":"10.1016\/j.icte.2023.11.001_b127","doi-asserted-by":"crossref","first-page":"3081","DOI":"10.1109\/TGRS.2011.2179050","article-title":"Satellite image time series analysis under time warping","volume":"50","author":"Petitjean","year":"2012","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.icte.2023.11.001_b128","unstructured":"X. Ning, C. Tang, W. Li, Z. Zhou, S. Liang, H. Yang, Y. Wang, Evaluating efficient performance estimators of neural architectures, in: Proceedings of the Neural Information Processing Systems, Vol. 34, 2021, pp. 12265\u201312277."},{"key":"10.1016\/j.icte.2023.11.001_b129","unstructured":"A. Krishnakumar, C. White, A. Zela, R. Tu, M. Safari, F. Hutter, NAS-Bench-Suite-Zero: Accelerating Research on Zero Cost Proxies, in: Proceedings of the Conference on Neural Information Processing Systems Datasets and Benchmarks Track, 2022."},{"key":"10.1016\/j.icte.2023.11.001_b130","unstructured":"H. Pham, M. Guan, B. Zoph, Q. Le, J. Dean, Efficient neural architecture search via parameters sharing, in: Proceedings of the International Conference on Machine Learning, 2018, pp. 4095\u20134104."},{"key":"10.1016\/j.icte.2023.11.001_b131","unstructured":"H. Liu, K. Simonyan, Y. Yang, DARTS: Differentiable Architecture Search, in: Proceedings of the International Conference on Learning Representations, 2019."},{"key":"10.1016\/j.icte.2023.11.001_b132","series-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"10.1016\/j.icte.2023.11.001_b133","unstructured":"T. Brown, B. Mann, N. Ryder, M. Subbiah, J.D. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell, S. Agarwal, A. Herbert-Voss, G. Krueger, T. Henighan, R. Child, A. Ramesh, D. Ziegler, J. Wu, C. Winter, C. Hesse, M. Chen, E. Sigler, M. Litwin, S. Gray, B. Chess, J. Clark, C. Berner, S. McCandlish, A. Radford, I. Sutskever, D. Amodei, Language models are few-shot learners, in: Proceedings of the Advances in Neural Information Processing Systems, Vol. 33, 2020, pp. 1877\u20131901."},{"key":"10.1016\/j.icte.2023.11.001_b134","doi-asserted-by":"crossref","unstructured":"D.H. Stolfi, E. Alba, X. Yao, Predicting car park occupancy rates in smart cities, in: Proceedings of the International Conference on Smart Cities, 2017, pp. 107\u2013117.","DOI":"10.1007\/978-3-319-59513-9_11"},{"key":"10.1016\/j.icte.2023.11.001_b135","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.enbuild.2017.01.083","article-title":"Data driven prediction models of energy use of appliances in a low-energy house","volume":"140","author":"Candanedo","year":"2017","journal-title":"Energy Build."},{"key":"10.1016\/j.icte.2023.11.001_b136","unstructured":"F.J.F. Urbano, E.A. Torres, BIN-CT: Sistema inteligente para la gesti\u00f3n de la recogida de residuos urbanos, in: Proceedings of the International Greencities Congress, 2018, pp. 187\u2013198."},{"issue":"4","key":"10.1016\/j.icte.2023.11.001_b137","doi-asserted-by":"crossref","first-page":"1821","DOI":"10.1109\/TPWRS.2004.835679","article-title":"Load forecasting using support vector machines: A study on EUNITE competition 2001","volume":"19","author":"Chen","year":"2004","journal-title":"IEEE Trans. Power Syst."},{"key":"10.1016\/j.icte.2023.11.001_b138","doi-asserted-by":"crossref","unstructured":"I. Radosavovic, J. Johnson, S. Xie, W.-Y. Lo, P. Doll\u00e1r, On network design spaces for visual recognition, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 1882\u20131890.","DOI":"10.1109\/ICCV.2019.00197"},{"key":"10.1016\/j.icte.2023.11.001_b139","doi-asserted-by":"crossref","unstructured":"T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Doll\u00e1r, C.L. Zitnick, Microsoft COCO: Common objects in context, in: Proceedings of the European Conference on Computer Vision, 2014, pp. 740\u2013755.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"10.1016\/j.icte.2023.11.001_b140","series-title":"One billion word benchmark for measuring progress in statistical language modeling","author":"Chelba","year":"2013"},{"key":"10.1016\/j.icte.2023.11.001_b141","unstructured":"A. Mehrotra, A.G.C. Ramos, S. Bhattacharya, \u0141. Dudziak, R. Vipperla, T. Chau, M.S. Abdelfattah, S. Ishtiaq, N.D. Lane, NAS-Bench-ASR: Reproducible neural architecture search for speech recognition, in: Proceedings of the International Conference on Learning Representations, 2020."},{"key":"10.1016\/j.icte.2023.11.001_b142","doi-asserted-by":"crossref","unstructured":"J.S. Garofolo, L.F. Lamel, W.M. Fisher, J.G. Fiscus, D.S. Pallett, DARPA TIMIT Acoustic-Phonetic Continous Speech Corpus CD-ROM. NIST Speech Disc 1-1.1, Vol. 93, 1993.","DOI":"10.6028\/NIST.IR.4930"},{"key":"10.1016\/j.icte.2023.11.001_b143","doi-asserted-by":"crossref","unstructured":"M. Tan, B. Chen, R. Pang, V. Vasudevan, M. Sandler, A. Howard, Q.V. Le, MnasNet: Platform-aware neural architecture search for mobile, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 2820\u20132828.","DOI":"10.1109\/CVPR.2019.00293"},{"key":"10.1016\/j.icte.2023.11.001_b144","unstructured":"D. Lee, M. Sugiyama, U. Luxburg, I. Guyon, R. Garnett, Matching networks for one shot learning, in: Proceedings of the Neural Information Processing Systems, Vol. 29, 2016, pp. 3637\u20133645."},{"key":"10.1016\/j.icte.2023.11.001_b145","series-title":"Meta-learning for semi-supervised few-shot classification","author":"Ren","year":"2018"},{"key":"10.1016\/j.icte.2023.11.001_b146","unstructured":"J. Lin, W.-M. Chen, J. Cohn, C. Gan, S. Han, MCUNet: Tiny Deep Learning on IoT Devices, in: Proceedings of the Conference on Neural Information Processing Systems, 2020, pp. 11711\u201311722."},{"key":"10.1016\/j.icte.2023.11.001_b147","unstructured":"J. Lin, W.-M. Chen, H. Cai, C. Gan, S. Han, MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning, in: Proceedings of the Conference on Neural Information Processing Systems, 2021."}],"container-title":["ICT Express"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2405959523001443?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2405959523001443?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T12:24:13Z","timestamp":1762518253000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2405959523001443"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":147,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,2]]}},"alternative-id":["S2405959523001443"],"URL":"https:\/\/doi.org\/10.1016\/j.icte.2023.11.001","relation":{},"ISSN":["2405-9595"],"issn-type":[{"value":"2405-9595","type":"print"}],"subject":[],"published":{"date-parts":[[2024,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Training-free neural architecture search: A review","name":"articletitle","label":"Article Title"},{"value":"ICT Express","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.icte.2023.11.001","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2023 The Author(s). Published by Elsevier B.V. on behalf of The Korean Institute of Communications and Information Sciences.","name":"copyright","label":"Copyright"}]}}