Optimal Synthesis of IDK-Cascades

Optimal Synthesis of IDK-Cascades
复制标题

IDK-Cascades 的优化合成

DOI:
10.1145/3453417.3453425
复制
发表时间:
2021
期刊:
Proceedings of the 29th International Conference on Real-Time and Network Systems (RTNS
影响因子:
--
通讯作者:
Wu, Yue
Wu, Yue
中科院分区:
--
文献类型:
--
作者:
Baruah, Sanjoy;Burns, Alan;Wu, Yue

文献摘要

参考文献

被引文献

相似文献

分类器是一种软件组件,通常基于深度学习(DL),将提供给它的每个输入分类为固定的“类”集合之一。IDK分类器可以附加地在某些输入上输出“我不知道”(IDK)。给定用于相同操作的几个不同的IDK分类器,考虑以这样的方式一致地使用它们的问题,使得成功地对任何输入进行分类的平均持续时间最小化。提出了解决这个问题的最佳算法,既可以是在一个额外的约束下,该操作必须在指定的硬截止日期内完成)。
A classifier is a software component, often based upon deep learning (DL), that categorizes each input provided to it into one of a fixed set of “classes”. An IDK classifier may additionally output an “I don’t know” (IDK) on certain input. Given several different IDK classifiers for the same operation, the problem is considered of using them in concert in such a manner that the average duration to successfully classify any input is minimized. Optimal algorithms are proposed for solving this problem, both as is and under an additional constraint that the operation must be completed within a specified hard deadline).
具有模糊数据的应用程序的分类方案
DOI: 10.1109/ijcnn.2000.859412
发表时间: 2000
期刊: Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium
影响因子: --
作者:
T. Trappenberg;A. Back
通讯作者: A. Back
具有随机执行时间的任务集的内存和时间高效可调度性分析
DOI: 10.1109/emrts.2001.933991
发表时间: 2001
期刊: Proceedings 13th Euromicro Conference on Real-Time Systems
影响因子: --
作者:
Sorin Manolache;P. Eles;Zebo Peng
通讯作者: Zebo Peng
DOI: 10.1145/1027794.1027797
发表时间: 2004-11
期刊: ACM Trans. Embed. Comput. Syst.
影响因子: --
作者:
Sorin Manolache;P. Eles;Zebo Peng
通讯作者: Sorin Manolache;P. Eles;Zebo Peng
一致%20预测%20for%20100%%20精度%20和%20应用%20到%20学习%20语义%20映射
DOI: 10.18653/v1/p16-1090
发表时间: 2016
期刊: ArXiv
影响因子: --
作者:
Fereshte Khani;M. Rinard;Percy Liang
通讯作者: Percy Liang