.png){kind=icon}
返回
Learning Hardware-Friendly Classifiers Through Algorithmic Stability
.png){kind=icon}
PRE
AI
DOI：10.1145/2836165.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Most state-of-the-art machine-learning (ML) algorithms do not consider the computational constraints of implementing the learned model on embedded devices. These constraints are, for example, the limited depth of the arithmetic unit, the memory availability, or the battery capacity. We propose a new learning framework, the Algorithmic Risk Minimization (ARM), which relies on Algorithmic-Stability, and includes these constraints inside the learning process itself. ARM allows one to train advanced resource-sparing ML models and to efficiently deploy them on smart embedded systems. Finally, we show the advantages of our proposal on a smartphone-based Human Activity Recognition application by comparing it to a conventional ML approach.
Keyword:
Support vector machines
hardware-friendly classifiers
bit-based classifiers
generalization performances
algorithmic stability
rademacher complexity
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
2.6
论文数:
237
被引数:
2.3K
机构
引用论文
.png){kind=icon}
分享收藏
查看更多内容