{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T04:11:48Z","timestamp":1751602308124,"version":"3.41.0"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031877711"},{"type":"electronic","value":"9783031877728"}],"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\/978-3-031-87772-8_18","type":"book-chapter","created":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T07:37:06Z","timestamp":1745307426000},"page":"211-222","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Development of\u00a0a\u00a0Transformer-Based Large Language Model Architecture in\u00a0Cloud"],"prefix":"10.1007","author":[{"given":"Theodor-Radu","family":"Grumeza","sequence":"first","affiliation":[]},{"given":"Thomas-Andrei","family":"Laz\u0103r","sequence":"additional","affiliation":[]},{"given":"Alexandra-Emilia","family":"Forti","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,4,23]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Al-Selwi, S.M., et al.: RNN-LSTM: from applications to modeling techniques and beyond-systematic review. J. King Saud Univ. Comput. Inf. Sci. 36, 102068 (2024)","DOI":"10.1016\/j.jksuci.2024.102068"},{"key":"18_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2023.104800","volume":"185","author":"T Breitenbach","year":"2024","unstructured":"Breitenbach, T., Malavalli Divakar, S., Rasbach, L., Jahnke, P.: MI-driven risk estimation for memory failure in a data center environment with convolutional neural networks, self-supervised data labeling and distribution-based model drift determination. J. Parallel Distrib. Comput. 185, 104800 (2024)","journal-title":"J. Parallel Distrib. Comput."},{"key":"18_CR3","unstructured":"Brown, T.B.: Language models are few-shot learners. arXiv preprint arXiv:2005.14165 (2020)"},{"key":"18_CR4","unstructured":"Cetin, E., Sun, Q., Zhao, T., Tang, Y.: An evolved universal transformer memory. arXiv preprint arXiv:2410.13166 (2024)"},{"key":"18_CR5","unstructured":"Cordonnier, J., Loukas, A., Jaggi, M.: Multi-head attention: Collaborate instead of concatenate. CoRR abs\/2006.16362 (2020). https:\/\/arxiv.org\/abs\/2006.16362"},{"issue":"3","key":"18_CR6","doi-asserted-by":"publisher","first-page":"733","DOI":"10.1162\/coli_a_00445","volume":"48","author":"P Dufter","year":"2022","unstructured":"Dufter, P., Schmitt, M., Sch\u00fctze, H.: Position information in transformers: an overview. Comput. Linguist. 48(3), 733\u2013763 (2022)","journal-title":"Comput. Linguist."},{"key":"18_CR7","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1007\/978-3-031-57942-4_7","volume-title":"Advanced Information Networking and Applications","author":"TR Grumeza","year":"2024","unstructured":"Grumeza, T.R., Laz\u0103r, T.A., Forti\u015f, A.E.: Social robots and edge computing: Integrating cloud robotics in social interaction. In: Barolli, L. (ed.) Advanced Information Networking and Applications, pp. 55\u201364. Springer Nature Switzerland, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-57942-4_7"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Grusky, M.: Rogue scores. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1914\u20131934 (2023)","DOI":"10.18653\/v1\/2023.acl-long.107"},{"key":"18_CR9","unstructured":"Kenton, J.D.M.W.C., Toutanova, L.K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT. vol.\u00a01, p.\u00a02. Minneapolis, Minnesota (2019)"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Ketkar, N., Moolayil, J., Ketkar, N., Moolayil, J.: Feed-forward neural networks. In: Deep Learning with Python: Learn Best Practices of Deep Learning Models with PyTorch, pp. 93\u2013131 (2021)","DOI":"10.1007\/978-1-4842-5364-9_3"},{"key":"18_CR11","unstructured":"Koroteev, M.V.: BERT: a review of applications in natural language processing and understanding. arXiv preprint arXiv:2103.11943 (2021)"},{"key":"18_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2023.113913","volume":"189","author":"Y Li","year":"2024","unstructured":"Li, Y., Cao, J., Xu, Y., Zhu, L., Dong, Z.Y.: Deep learning based on transformer architecture for power system short-term voltage stability assessment with class imbalance. Renew. Sustain. Energy Rev. 189, 113913 (2024)","journal-title":"Renew. Sustain. Energy Rev."},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Sandler, M., Zhmoginov, A., Vladymyrov, M., Jackson, A.: Fine-tuning image transformers using learnable memory. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12155\u201312164, June 2022","DOI":"10.1109\/CVPR52688.2022.01184"},{"key":"18_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.physd.2019.132306","volume":"404","author":"A Sherstinsky","year":"2020","unstructured":"Sherstinsky, A.: Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Physica D 404, 132306 (2020)","journal-title":"Physica D"},{"key":"18_CR15","unstructured":"Touvron, H., et al.: LLaMA: open and efficient foundation language models (2023). https:\/\/arxiv.org\/abs\/2302.13971"},{"key":"18_CR16","unstructured":"Vaswani, A.: Attention is all you need. In: Advances in Neural Information Processing Systems (2017)"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Wang, Y.A., Chen, Y.N.: What do position embeddings learn? an empirical study of pre-trained language model positional encoding. arXiv preprint arXiv:2010.04903 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.555"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Wu, C., Wu, F., Ge, S., Qi, T., Huang, Y., Xie, X.: Neural news recommendation with multi-head self-attention. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 6389\u20136394 (2019)","DOI":"10.18653\/v1\/D19-1671"},{"key":"18_CR19","doi-asserted-by":"publisher","unstructured":"Wu, Y., Zhao, Y., Hu, B., Minervini, P., Stenetorp, P., Riedel, S.: An efficient memory-augmented transformer for knowledge-intensive NLP tasks. In: Goldberg, Y., Kozareva, Z., Zhang, Y. (eds.) Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 5184\u20135196. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates, December 2022. https:\/\/doi.org\/10.18653\/v1\/2022.emnlp-main.346","DOI":"10.18653\/v1\/2022.emnlp-main.346"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Xie, C.W., Wu, J., Zheng, Y., Pan, P., Hua, X.S.: Token embeddings alignment for cross-modal retrieval. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 4555\u20134563 (2022)","DOI":"10.1145\/3503161.3548107"},{"key":"18_CR21","doi-asserted-by":"publisher","unstructured":"Zhou, X., Liu, H., Shi, C., Liu, J.: Chapter 2 - the basics of deep learning. In: Zhou, X., Liu, H., Shi, C., Liu, J. (eds.) Deep Learning on Edge Computing Devices, pp. 19\u201336. Elsevier (2022).https:\/\/doi.org\/10.1016\/B978-0-32-385783-3.00009-0, https:\/\/www.sciencedirect.com\/science\/article\/pii\/B9780323857833000090","DOI":"10.1016\/B978-0-32-385783-3.00009-0"}],"container-title":["Lecture Notes on Data Engineering and Communications Technologies","Advanced Information Networking and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-87772-8_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T18:37:57Z","timestamp":1751567877000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-87772-8_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031877711","9783031877728"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-87772-8_18","relation":{},"ISSN":["2367-4512","2367-4520"],"issn-type":[{"type":"print","value":"2367-4512"},{"type":"electronic","value":"2367-4520"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"23 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AINA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Advanced Information Networking and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Barcelona","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","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":"9 April 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 April 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"39","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aina0","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/voyager.ce.fit.ac.jp\/conf\/aina\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}