Optimally ordering IDK classifiers subject to deadlines

Optimally ordering IDK classifiers subject to deadlines
复制标题

根据截止日期优化订购 IDK 分类器

DOI:
10.1007/s11241-022-09383-w
复制
发表时间:
2022
期刊:
影响因子:
1.3
通讯作者:
Wu, Yue
Wu, Yue
中科院分区:
计算机科学3区
文献类型:
--
作者:
Baruah, Sanjoy;Burns, Alan;Davis, Robert I.;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,将提供给它的每个输入分类到一组固定的类中。IDK分类器可另外针对某些输入输出“我不知道”(IDK)。多个不同的IDK分类器可用于相同的分类问题,从而在有效性(即成功分类的概率)和效率(即执行时间)之间提供不同的权衡。最佳离线算法提出顺序排序IDK分类器,使预期的持续时间,成功地分类输入最小化,可选地受到一个硬的最后期限上的最大时间允许分类。解决方案提供考虑独立和依赖的分类器对之间的关系,以及两者的混合。
A classifier is a software component, often based on Deep Learning, that categorizes each input provided to it into one of a fixed set of classes. An IDK classifier may additionally output “I Don’t Know” (IDK) for certain inputs. Multiple distinct IDK classifiers may be available for the same classification problem, offering different trade-offs between effectiveness, i.e. the probability of successful classification, and efficiency, i.e. execution time. Optimal offline algorithms are proposed for sequentially ordering IDK classifiers such that the expected duration to successfully classify an input is minimized, optionally subject to a hard deadline on the maximum time permitted for classification. Solutions are provided considering independent and dependent relationships between pairs of classifiers, as well as a mix of the two.
IDK-Cascades 的优化合成
DOI: 10.1145/3453417.3453425
发表时间: 2021
期刊: Proceedings of the 29th International Conference on Real-Time and Network Systems (RTNS
影响因子: --
作者:
Baruah, Sanjoy;Burns, Alan;Wu, Yue
通讯作者: Wu, Yue
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
探索图像大小调整以优化基于关键性的机器感知
DOI: 10.1109/rtcsa52859.2021.00027
发表时间: 2021
期刊: 2021 IEEE 27th International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA)
影响因子: --
作者:
Yigong Hu;Shengzhong Liu;T. Abdelzaher;Maggie B. Wigness;P. David
通讯作者: P. David
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