{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,12]],"date-time":"2024-09-12T22:28:10Z","timestamp":1726180090982},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031216886"},{"type":"electronic","value":"9783031216893"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-21689-3_10","type":"book-chapter","created":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T10:03:56Z","timestamp":1668765836000},"page":"123-138","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Training Aware Sigmoidal Optimization"],"prefix":"10.1007","author":[{"ORCID":"http:\/\/orcid.org\/0000-0002-2527-4548","authenticated-orcid":false,"given":"David","family":"Mac\u00eado","sequence":"first","affiliation":[]},{"given":"Pedro","family":"Dreyer","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-8980-6742","authenticated-orcid":false,"given":"Teresa","family":"Ludermir","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0001-6421-9747","authenticated-orcid":false,"given":"Cleber","family":"Zanchettin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,19]]},"reference":[{"unstructured":"Touvron, H., Vedaldi, A., Douze, M., Jegou, H.: Fixing the train-test resolution discrepancy. In: Neural Information Processing Systems, pp. 8252\u20138262 (2019)","key":"10_CR1"},{"doi-asserted-by":"crossref","unstructured":"Park, D.S.: \u201cImproved noisy student training for automatic speech recognition. In: Annual Conference of the International Speech Communication Association, pp. 2817\u20132821 (2020)","key":"10_CR2","DOI":"10.21437\/Interspeech.2020-1470"},{"unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Association for Computational Linguistics: Human Language Technologies, pp. 4171\u20134186 (2019)","key":"10_CR3"},{"issue":"3","key":"10_CR4","doi-asserted-by":"publisher","first-page":"292","DOI":"10.3390\/electronics8030292","volume":"8","author":"M Alom","year":"2019","unstructured":"Alom, M., et al.: A state-of-the-art survey on deep learning theory and architectures. Electronics 8(3), 292\u2013358 (2019)","journal-title":"Electronics"},{"unstructured":"Schmidt, R.M., Schneider, F., Hennig, P.: Descending through a crowded valley - benchmarking deep learning optimizers, CoRR, vol. abs\/ arXiv: 2007.01547 (2020)","key":"10_CR5"},{"key":"10_CR6","first-page":"2121","volume":"12","author":"J Duchi","year":"2011","unstructured":"Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. M. L. Res. 12, 2121\u20132159 (2011)","journal-title":"J. M. L. Res."},{"unstructured":"Dauphin, Y.N., Pascanu, R., G\u00fcl\u00e7ehre, \u00c7., Cho, K., Ganguli, S., Bengio, Y.: Identifying and attacking the saddle point problem in high-dimensional non-convex optimization. In: Neural Information Processing Systems, pp. 2933\u20132941 (2014)","key":"10_CR7"},{"unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. In: International Conference on Learning Representations (2015)","key":"10_CR8"},{"unstructured":"Tieleman, T., Hinton, G.: RMSProp: Divide the gradient by a running average of its recent magnitude. In: Neural Networks for Machine Learning (2012)","key":"10_CR9"},{"unstructured":"Wilson, A.C., Roelofs, R., Stern, M., Srebro, N., Recht, B.: The marginal value of adaptive gradient methods in machine learning. In: NeurIPS, pp. 4148\u20134158 (2017)","key":"10_CR10"},{"issue":"11","key":"10_CR11","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y Lecun","year":"1998","unstructured":"Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. of the IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. of the IEEE"},{"unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015)","key":"10_CR12"},{"doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","key":"10_CR13","DOI":"10.1109\/CVPR.2016.90"},{"unstructured":"Krizhevsky, A.: Learning multiple layers of features from tiny images. Technical Report, University of Toronto (2009)","key":"10_CR14"},{"issue":"5","key":"10_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/0041-5553(64)90137-5","volume":"4","author":"B Polyak","year":"1964","unstructured":"Polyak, B.: Some methods of speeding up the convergence of iteration methods. USSR Comp. Math. and Math. Phys. 4(5), 1\u201317 (1964)","journal-title":"USSR Comp. Math. and Math. Phys."},{"unstructured":"Graves, A.: Generating sequences with recurrent neural networks, CoRR, vol. abs\/ arxiv: 1308.0850 (2013)","key":"10_CR16"},{"unstructured":"Reddi, S.J., Kale, S., Kumar, S.: On the convergence of adam and beyond. In: International Conference on Learning Representations (2018)","key":"10_CR17"},{"doi-asserted-by":"crossref","unstructured":"Tishby, N., Zaslavsky, N.: Deep learning and the information bottleneck principle. In: IEEE Information Theory Workshop, pp. 1\u20135 (2015)","key":"10_CR18","DOI":"10.1109\/ITW.2015.7133169"},{"unstructured":"Krizhevsky, A.: Learning multiple layers of features from tiny images. Learning multiple layers of features from tiny images, Science Department, University of Toronto (2009)","key":"10_CR19"}],"container-title":["Lecture Notes in Computer Science","Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-21689-3_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,21]],"date-time":"2022-11-21T00:12:29Z","timestamp":1668989549000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-21689-3_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031216886","9783031216893"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-21689-3_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"19 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"BRACIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brazilian Conference on Intelligent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Campinas","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brazil","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bracis2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www2.sbc.org.br\/bracis2022\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"JEMS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"225","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"89","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"40% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}