{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T19:05:14Z","timestamp":1770750314125,"version":"3.50.0"},"reference-count":51,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Canada\u2019s International Development Research Centre, Ottawa, Canada","award":["109704-001\/002"],"award-info":[{"award-number":["109704-001\/002"]}]},{"name":"Swedish International Development Cooperation Agency","award":["109704-001\/002"],"award-info":[{"award-number":["109704-001\/002"]}]},{"name":"AI4D Anglophone Africa Multidisciplinary Research Lab","award":["109704-001\/002"],"award-info":[{"award-number":["109704-001\/002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>Applying deep learning models requires design and optimization when solving multifaceted artificial intelligence tasks. Optimization relies on human expertise and is achieved only with great exertion. The current literature concentrates on automating design; optimization needs more attention. Similarly, most existing optimization libraries focus on other machine learning tasks rather than image classification. For this reason, an automated optimization scheme of deep learning models for image classification tasks is proposed in this paper. A sequential-model-based optimization algorithm was used to implement the proposed method. Four deep learning models, a transformer-based model, and standard datasets for image classification challenges were employed in the experiments. Through empirical evaluations, this paper demonstrates that the proposed scheme improves the performance of deep learning models. Specifically, for a Virtual Geometry Group (VGG-16), accuracy was heightened from 0.937 to 0.983, signifying a 73% relative error rate drop within an hour of automated optimization. Similarly, training-related parameter values are proposed to improve the performance of deep learning models. The scheme can be extended to automate the optimization of transformer-based models. The insights from this study may assist efforts to provide full access to the building and optimization of DL models, even for amateurs.<\/jats:p>","DOI":"10.3390\/computers12090174","type":"journal-article","created":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T08:19:39Z","timestamp":1693556379000},"page":"174","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Automated Optimization-Based Deep Learning Models for Image Classification Tasks"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5316-7486","authenticated-orcid":false,"given":"Daudi Mashauri","family":"Migayo","sequence":"first","affiliation":[{"name":"School of Computational and Communicational Science and Engineering, The Nelson Mandela African Institution of Science and Technology, Arusha 23311, Tanzania"},{"name":"Department of Business Administration, Tanzania Institute of Accountancy (TIA), Dar es Salaam 15108, Tanzania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9443-957X","authenticated-orcid":false,"given":"Shubi","family":"Kaijage","sequence":"additional","affiliation":[{"name":"School of Computational and Communicational Science and Engineering, The Nelson Mandela African Institution of Science and Technology, Arusha 23311, Tanzania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stephen","family":"Swetala","sequence":"additional","affiliation":[{"name":"Department of Orthopedic and Trauma Surgery, Bugando Medical Centre, Mwanza 33102, Tanzania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3763-9302","authenticated-orcid":false,"given":"Devotha G.","family":"Nyambo","sequence":"additional","affiliation":[{"name":"School of Computational and Communicational Science and Engineering, The Nelson Mandela African Institution of Science and Technology, Arusha 23311, Tanzania"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,9,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"S36","DOI":"10.1016\/j.metabol.2017.01.011","article-title":"Artificial intelligence in medicine","volume":"69","author":"Hamet","year":"2017","journal-title":"Metabolism"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1007\/s12551-018-0449-9","article-title":"Machine learning: Applications of artificial intelligence to imaging and diagnosis","volume":"11","author":"Nichols","year":"2019","journal-title":"Biophys. Rev."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1109\/TPAMI.1981.4767059","article-title":"Principles of Artificial Intelligence","volume":"PAMI-3","author":"Nilsson","year":"1981","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Zhang, X.-D. (2020). Machine Learning, Springer.","DOI":"10.1007\/978-981-15-2770-8_6"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Alpaydin, E. (2020). Introduction to Machine Learning, MIT Press.","DOI":"10.7551\/mitpress\/13811.001.0001"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"El Naqa, I., and Murphy, M.J. (2015). Machine Learning in Radiation Oncology, Springer.","DOI":"10.1007\/978-3-319-18305-3"},{"key":"ref_7","unstructured":"Mitchell, T. (1997). Machine Learning, McGraw-Hill Science."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Mohammed, M., Khan, M.B., and Bashier, E.B.M. (2017). Machine Learning: Algorithms and Applications, CRC Press.","DOI":"10.1201\/9781315371658"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1153","DOI":"10.1109\/TMI.2016.2553401","article-title":"Guest Editorial Deep Learning in Medical Imaging: Overview and Future Promise of an Exciting New Technique","volume":"35","author":"Greenspan","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"106622","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":"ref_12","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"Bergstra","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1077","DOI":"10.1109\/TNS.2010.2045898","article-title":"Maximum-likelihood estimation with a contracting-grid search algorithm","volume":"57","author":"Hesterman","year":"2010","journal-title":"IEEE Trans. Nucl. Sci."},{"key":"ref_14","unstructured":"Dewancker, I., McCourt, M., Clark, C., and Peter, P.E. Hart, Bayesian Optimization Primer, Wiley. Available online: https:\/\/static.sigopt.com\/b\/20a144d208ef255d3b981ce419667ec25d8412e2\/static\/pdf\/SigOpt_Bayesian_Optimization_Primer.pdf."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1109\/JPROC.2015.2494218","article-title":"Taking the human out of the loop: A review of bayesian optimization","volume":"104","author":"Shahriari","year":"2015","journal-title":"Proc. IEEE"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1889","DOI":"10.1162\/089976600300015187","article-title":"Gradient-Based Optimization of Hyperparameters","volume":"12","author":"Bengio","year":"2000","journal-title":"Neural Comput."},{"key":"ref_17","unstructured":"Chandra, K., Xie, A., Ragan-Kelley, J., and Meijer, E. (2019). Gradient Descent: The Ultimate Optimizer. arXiv."},{"key":"ref_18","unstructured":"Franceschi, L., Donini, M., Frasconi, P., and Pontil, M. (2017, January 6\u201311). Forward And Reverse Gradient-Based Hyperparameter Optimization. Proceedings of the 34th International Conference on Machine Learning, Sydney, Australia."},{"key":"ref_19","unstructured":"Maclaurin, D., Duvenaud, D., and Adams, R. (2015, January 7\u20139). Gradient-Based Hyperparameter Optimization through Reversible Learning. Proceedings of the 32nd International Conference on Machine Learning, Lille, France."},{"key":"ref_20","unstructured":"Claesen, M., and De Moor, B. (2015). Hyperparameter search in machine learning. arXiv."},{"key":"ref_21","unstructured":"Bergstra, J., Yamins, D., and Cox, D. (2013, January 17\u201319). Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures. Proceedings of the 30th International Conference on Machine Learning, Atlanta, GE, USA."},{"key":"ref_22","unstructured":"(2023, February 01). Scikit, Scikit-Optimize: Sequential Model-Based Optimization in Python\u2014Scikit-Optimize 0.8.1 Documentation. Available online: https:\/\/scikit-optimize.github.io\/stable\/."},{"key":"ref_23","first-page":"1","article-title":"GitHub\u2014automl\/SMAC3: SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization","volume":"23","author":"Lindauer","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref_24","unstructured":"Cai, H., Zhu, L., and Han, S. (2019, January 6\u20139). Proxylessnas: Direct neural architecture search on target task and hardware. Proceedings of the 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA."},{"key":"ref_25","unstructured":"Liu, C., Zoph, B., Neumann, M., Shlens, J., Hua, W., Li, L.J., Li, F.-F., Yuille, A., Huang, J., and Murphy, K. (2018). Lecture Notes in Computer Science (Including Subseries Lecture Notes Artificial Intelligence Lecture Notes Bioinformatics), Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, 8\u201314 September 2018, Springer."},{"key":"ref_26","unstructured":"Pham, H., Guan, M., Zoph, B., Le, Q., and Dean, J. (2018, January 10\u201315). Efficient neural architecture search via parameters sharing. Proceedings of the 5th International Conference on Machine Learning, Stockholm, Sweden."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Tan, M., Chen, B., Pang, R., Vasudevan, V., Sandler, M., Howard, A., and Le, Q.V. (2019, January 15\u201320). Mnasnet: Platform-aware neural architecture search for mobile. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref_28","unstructured":"Zoph, B., and Le, Q.V. (2017, January 24\u201326). Neural architecture search with reinforcement learning. Proceedings of the 5th International Conference on Learning Representations, ICLR 2017, Conference Track Proceedings, Toulon, France."},{"key":"ref_29","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016, January 27\u201330). Rethinking the Inception Architecture for Computer Vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_32","unstructured":"Tan, M., and Le, Q. (2019, January 9\u201315). Efficientnet: Rethinking Model Scaling for Convolutional Neural Networks. Proceedings of the 36th International Conference on Machine Learning, Long Beach, CA, USA."},{"key":"ref_33","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Houlsby, N. (2020). An Image Is Worth 16\u00d716 Words: Transformers for Image Recognition at Scale. arXiv."},{"key":"ref_34","unstructured":"Pinto, F., Torr, P.H.S., and Dokania, P.K. (2022). Lecture Notes in Computer Science, Computer Vision\u2014ECCV 2022, Proceedings of the 17th European Conference, Tel Aviv, Israel, 23\u201327 October 2022, Springer."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1016\/j.procs.2018.05.198","article-title":"An Analysis of Convolutional Neural Networks for Image Classification","volume":"132","author":"Sharma","year":"2018","journal-title":"Procedia Comput. Sci."},{"key":"ref_36","unstructured":"Birodkar, V., Mobahi, H., and Bengio, S. (2019). Semantic Redundancies in Image-Classification Datasets: The 10% You Don\u2019t Need. arXiv."},{"key":"ref_37","unstructured":"Xiao, H., Rasul, K., and Vollgraf, R. (2017). Fashion-MNIST: A Novel Image Dataset for Benchmarking Machine Learning Algorithms. arXiv."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., and Fei-Fei, L. (2013, January 2\u20138). 3D Object representations for fine-grained categorization. Proceedings of the 2013 IEEE International Conference on Computer Vision Workshops, Sydney, NSW, Australia.","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Wang, Y., Sun, D., Chen, K., Lai, F., and Chowdhury, M. (2022). Egeria: Efficient DNN Training with Knowledge-Guided Layer Freezing. arXiv.","DOI":"10.1145\/3552326.3587451"},{"key":"ref_40","unstructured":"Probst, P., Bischl, B., and Boulesteix, A.L. (2018). Tunability: Importance of Hyperparameters of Machine Learning Algorithms. arXiv."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"e232","DOI":"10.1016\/S2589-7500(19)30108-6","article-title":"Automated deep learning design for medical image classification by health-care professionals with no coding experience: A feasibility study","volume":"1","author":"Faes","year":"2019","journal-title":"Lancet Digit. Health"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Xu, H., Yao, L., Li, Z., Liang, X., and Zhang, W. (November, January 27). Auto-FPN: Automatic network architecture adaptation for object detection beyond classification. Proceedings of the 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.","DOI":"10.1109\/ICCV.2019.00675"},{"key":"ref_43","unstructured":"Weerts, H.J., Mueller, A.C., and Vanschoren, J. (2020). Importance of Tuning Hyperparameters of Machine Learning Algorithms. arXiv."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Guo, J., Han, K., Wang, Y., Zhang, C., Yang, Z., Wu, H., Chen, X., and Xu, C. (2020, January 13\u201319). Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01142"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"He, X., Wang, S., Chu, X., Shi, S., Tang, J., Liu, X., Yan, C., Zhang, J., and Ding, G. (2021, January 2\u20139). Automated Model Design and Benchmarking of Deep Learning Models for COVID-19 Detection with Chest CT Scans. Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21), virtually.","DOI":"10.1609\/aaai.v35i6.16614"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"5486","DOI":"10.1109\/TITS.2020.2987614","article-title":"An Automated Hyperparameter Search-Based Deep Learning Model for Highway Traffic Prediction","volume":"22","author":"Yi","year":"2020","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1016\/j.icte.2020.04.010","article-title":"The effect of batch size on the generalizability of the convolutional neural networks on a histopathology dataset","volume":"6","author":"Kandel","year":"2020","journal-title":"ICT Express"},{"key":"ref_48","unstructured":"Masters, D., and Luschi, C. (2018). Revisiting small batch training for deep neural networks. arXiv."},{"key":"ref_49","first-page":"20","article-title":"Impact of training set batch size on the performance of convolutional neural networks for diverse datasets","volume":"20","author":"Radiuk","year":"2017","journal-title":"Inf. Technol. Manag. Sci."},{"key":"ref_50","unstructured":"Bengio, Y. (2012). Neural Networks: Tricks of the Trade, Springer. [2nd ed.]."},{"key":"ref_51","unstructured":"Touvron, H., Cord, M., El-Nouby, A., Verbeek, J., and J\u00e9gou, H. (2022). Lecture Notes in Computer Science (Including Subseries Lecture Notes Artificial Intelligence Lecture Notes Bioinformatics), Springer."}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/12\/9\/174\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:44:59Z","timestamp":1760129099000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/12\/9\/174"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,1]]},"references-count":51,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2023,9]]}},"alternative-id":["computers12090174"],"URL":"https:\/\/doi.org\/10.3390\/computers12090174","relation":{},"ISSN":["2073-431X"],"issn-type":[{"value":"2073-431X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,1]]}}}