Proposed for presentation at the Science and Technology Conference 2020 held June 28, 2021 - November 02, 2020 in Vienna, Austria.最新文献

筛选

英文中文

Domain Informed - a better approach to regularization and semi-supervised learning for seismic event analysis. 领域信息——地震事件分析中一种更好的正则化和半监督学习方法。

Proposed for presentation at the Science and Technology Conference 2020 held June 28, 2021 - November 02, 2020 in Vienna, Austria. Pub Date : 2020-11-01 DOI: 10.2172/1829553

L. Linville

{"title":"Domain Informed - a better approach to regularization and semi-supervised learning for seismic event analysis.","authors":"L. Linville","doi":"10.2172/1829553","DOIUrl":"https://doi.org/10.2172/1829553","url":null,"abstract":"Typically, data-driven learning works best when we can exploit expectations from our data domain. For example, the development of recurrent neural network architectures to deal with the temporal dependence in language, geometric deep learning for 3-D problems, and physics-constrained Bayesian learning for more interpretable dependencies. Yet it can be unclear how to interject expectations, and which specific expectations will result in better outcomes for a given domain. In seismic event processing, enforcing consistency over disparate observations for an individual event has a long history of empirical value. For example, we almost always use magnitude estimates from many individual stations, drop outliers, and average to arrive at a final event magnitude. Similarly, we can leverage the expectation that stations provide consistent predictions for any event-level attributes, such as event type, when we develop deep learning based predictive models. In this work we show how to formulate this expectation as a loss term during model training and give several examples of how this expectation can result in better model regularization, which can reduce overfitting while still outperforming other methods, give us more trustworthy decision confidence, and allows us to leverage data where no ground truth is available.","PeriodicalId":233836,"journal":{"name":"Proposed for presentation at the Science and Technology Conference 2020 held June 28, 2021 - November 02, 2020 in Vienna, Austria.","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123951772","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0