{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T08:10:06Z","timestamp":1751011806824,"version":"3.41.0"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031969614","type":"print"},{"value":"9783031969621","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-96962-1_6","type":"book-chapter","created":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T07:34:07Z","timestamp":1751009647000},"page":"81-97","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Small-to-Large: Proportional Uniform Distribution Weights Transferring to\u00a0Reduce Energy Consumption of\u00a0Training the\u00a0Models with\u00a0Fully Connected Layers"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7865-5822","authenticated-orcid":false,"given":"Farzad","family":"Vazinram","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,28]]},"reference":[{"key":"6_CR1","first-page":"1","volume":"23","author":"W Fedus","year":"2022","unstructured":"Fedus, W., Zoph, B., Shazeer, N.: Switch transformers: scaling to trillion parameter models with simple and efficient sparsity. J. Mach. Learn. Res. 23, 1\u201339 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"6_CR2","unstructured":"Desislavov, R., Mart\u00ednez-Plumed, F., Hern\u00e1ndez-Orallo, J.: Compute and energy consumption trends in deep learning inference, arXiv [cs.LG], 12-Sep-2021"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Yang, T.-J. ., Chen, Y.-H., Sze, V.: Designing energy-efficient convolutional neural networks using energy-aware pruning, arXiv [cs.CV], 15-Nov-2016","DOI":"10.1109\/CVPR.2017.643"},{"key":"6_CR4","doi-asserted-by":"publisher","unstructured":"Yang, T.-J., Chen, Y.-H., Emer, J., Sze, V.: A method to estimate the energy consumption of deep neural networks,\" 2017 51st Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA, USA, 2017, pp. 1916\u20131920. https:\/\/doi.org\/10.1109\/ACSSC.2017.8335698.","DOI":"10.1109\/ACSSC.2017.8335698."},{"issue":"6","key":"6_CR5","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60(6), 84\u201390 (2017)","journal-title":"Commun. ACM"},{"key":"6_CR6","unstructured":"Dai, B., Zhu, C., Wipf, D.: Compressing neural networks using the variational information bottleneck. In: International Conference on Machine Learning (2018)"},{"key":"6_CR7","unstructured":"Courbariaux, M., Bengio, Y., David, J.P.: BinaryConnect: training deep neural networks with binary weights during propagations. In: Proceedings of the 29th International Conference on Neural Information Processing Systems - Volume 2, Montreal, Canada, 2015, pp. 3123\u20133131 (2015)"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Velez, D., Santa, S., Patino, G.: MLP neural network based on PCA and K-means clustering for PM2.5 forecasting. In: Computing, Internet of Things and Data Analytics, 2024, pp. 202\u2013212 (2024)","DOI":"10.1007\/978-3-031-53717-2_19"},{"issue":"12","key":"6_CR9","doi-asserted-by":"publisher","first-page":"14680","DOI":"10.1007\/s11227-022-04475-7","volume":"78","author":"K Spurlock","year":"2022","unstructured":"Spurlock, K., Elgazzar, H.: A genetic mixed-integer optimization of neural network hyper-parameters. J. Supercomput. 78(12), 14680\u201314702 (2022)","journal-title":"J. Supercomput."},{"key":"6_CR10","unstructured":"Courty, B., et al., \u2018mlco2\/codecarbon: v2.4.1\u2019. Zenodo (May 2024)"},{"issue":"5","key":"6_CR11","doi-asserted-by":"publisher","first-page":"2900","DOI":"10.1109\/TPAMI.2023.3334614","volume":"46","author":"Y He","year":"2024","unstructured":"He, Y., Xiao, L.: Structured pruning for deep convolutional neural networks: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 46(5), 2900\u20132919 (2024). https:\/\/doi.org\/10.1109\/TPAMI.2023.3334614","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR12","unstructured":"Mocanu, D.C., et al.: Sparse Training Theory for Scalable and Efficient Agents, arXiv [cs.AI], 02-Mar-2021"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Koanantakool, P., et al.: Communication-avoiding parallel sparse-dense matrix-matrix multiplication. In: 2016 IEEE International Parallel and Distributed Processing Symposium (IPDPS) (2016)","DOI":"10.1109\/IPDPS.2016.117"},{"key":"6_CR14","unstructured":"Wheatman, B., Madhyastha, M., Burns, R.: Masked matrix multiplication for emergent sparsity. ArXiv:abs\/2402.14118 (2024)"},{"key":"6_CR15","unstructured":"Wesselink, W., Grooten, B., Xiao, Q., de Campos, C., Pechenizkiy, M.: Nerva: a truly sparse implementation of neural networks, arXiv [cs.LG]. (2024)"},{"issue":"2","key":"6_CR16","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/s11063-024-11578-0","volume":"56","author":"FZ El-Hassani","year":"2024","unstructured":"El-Hassani, F.Z., Amri, M., Joudar, N.-E., Haddouch, K.: A new optimization model for mlp hyperparameter tuning: modeling and resolution by real-coded genetic algorithm. Neural Process. Lett. 56(2), 105 (2024)","journal-title":"Neural Process. Lett."},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"Dietterich, T.G.: Ensemble methods in machine learning. In: multiple classifier systems, 2000, pp. 1\u201315 (2000)","DOI":"10.1007\/3-540-45014-9_1"},{"key":"6_CR18","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: NIPS 2014 Deep Learning Workshop, arXiv [stat.ML] (2015)"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: \u2018Revisiting the transferability of supervised pretraining: an MLP perspective. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022, pp. 9173\u20139183 (2022)","DOI":"10.1109\/CVPR52688.2022.00897"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Gale, T., Zaharia, M., Young, C., Elsen, E.: Sparse GPU kernels for deep learning. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (2020)","DOI":"10.1109\/SC41405.2020.00021"},{"key":"6_CR21","unstructured":"Nvidia, \u2018CuSPARSE\u2019. https:\/\/docs.nvidia.com\/cuda\/cusparse\/. Accessed 12 Jan 2025"},{"issue":"3","key":"6_CR22","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","volume":"17","author":"P Virtanen","year":"2020","unstructured":"Virtanen, P., et al.: SciPy 1.0: fundamental algorithms for scientific computing in Python. Nat. Methods 17(3), 261\u2013272 (2020)","journal-title":"Nat. Methods"},{"key":"6_CR23","unstructured":"Abadi, M., et al.:\u2018TensorFlow: a system for large-scale machine learning\u2019. In: 12th $${USENIX} Symposium on Operating Systems Design and Implementation ({OSDI}$$ 16), pp. 265\u2013283 (2016)"},{"key":"6_CR24","unstructured":"Gu, X., Liu, L., Yu, H., Li, J., Chen, C., Han, J.: On the Transformer growth for progressive BERT training, arXiv [cs.CL], 23-Oct-2020"},{"key":"6_CR25","unstructured":"Krizhevsky, A.: Learning Multiple Layers of Features from Tiny Images, University of Toronto (05 2012)"},{"issue":"6","key":"6_CR26","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1109\/MSP.2012.2211477","volume":"29","author":"L Deng","year":"2012","unstructured":"Deng, L.: The MNIST database of handwritten digit images for machine learning research. IEEE Signal Process. Mag. 29(6), 141\u2013142 (2012)","journal-title":"IEEE Signal Process. Mag."},{"key":"6_CR27","unstructured":"Chollet, F., et al.:\u2018Keras\u2019 (2015). https:\/\/github.com\/fchollet\/keras"}],"container-title":["Lecture Notes in Computer Science","Computational Science and Its Applications \u2013 ICCSA 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-96962-1_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T07:34:16Z","timestamp":1751009656000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-96962-1_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031969614","9783031969621"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-96962-1_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"28 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCSA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Science and Its Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Istanbul","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"T\u00fcrkiye","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccsa2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iccsa.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}