人类反馈促进NLU-ML模型的持续学习机制

2019 International Conference on Computational Intelligence in Data Science (ICCIDS) Pub Date : 2019-02-01 DOI:10.1109/ICCIDS.2019.8862102

G. Abinaya, Gyan Ranjan, P. Aswin Karthik

{"title":"人类反馈促进NLU-ML模型的持续学习机制","authors":"G. Abinaya, Gyan Ranjan, P. Aswin Karthik","doi":"10.1109/ICCIDS.2019.8862102","DOIUrl":null,"url":null,"abstract":"In this paper, we propose a novel framework that enables a machine learning model to constantly learn over a period of time and hence improve the performance with time and more data. We have compared the performance of different models which were trained only on the actual data against models trained with the data aided by the feedback collected by the automated framework.","PeriodicalId":196915,"journal":{"name":"2019 International Conference on Computational Intelligence in Data Science (ICCIDS)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Continuous learning mechanism of NLU-ML models boosted by human feedback\",\"authors\":\"G. Abinaya, Gyan Ranjan, P. Aswin Karthik\",\"doi\":\"10.1109/ICCIDS.2019.8862102\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, we propose a novel framework that enables a machine learning model to constantly learn over a period of time and hence improve the performance with time and more data. We have compared the performance of different models which were trained only on the actual data against models trained with the data aided by the feedback collected by the automated framework.\",\"PeriodicalId\":196915,\"journal\":{\"name\":\"2019 International Conference on Computational Intelligence in Data Science (ICCIDS)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-02-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2019 International Conference on Computational Intelligence in Data Science (ICCIDS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICCIDS.2019.8862102\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 International Conference on Computational Intelligence in Data Science (ICCIDS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCIDS.2019.8862102","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 3

摘要

在本文中，我们提出了一个新的框架，使机器学习模型能够在一段时间内不断学习，从而随着时间和数据的增加而提高性能。我们比较了仅在实际数据上训练的不同模型的性能，以及使用自动化框架收集的反馈辅助数据训练的模型的性能。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

Continuous learning mechanism of NLU-ML models boosted by human feedback

In this paper, we propose a novel framework that enables a machine learning model to constantly learn over a period of time and hence improve the performance with time and more data. We have compared the performance of different models which were trained only on the actual data against models trained with the data aided by the feedback collected by the automated framework.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2019 International Conference on Computational Intelligence in Data Science (ICCIDS)

自引率

0.00%

发文量