知识卡片
学习适合规则难显式表达的任务
语音或图像任务往往难用手工规则穷举,数据学习可利用样本中的模式。其优势并非“传统程序不能处理大数据”,训练和推断本身也依赖程序;是否采用仍需任务目标、数据质量和验证条件。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
已有反馈 · 0 条
还没有人提交反馈。
在整书笔记中的位置
原书出处 · 1 处
- · 查看原书依据
ML algorithms are used in a wide variety of applications, such as in engineering, medicine, email filtering, speech recognition, agriculture, computer vision, facial recognition, signal processing, and cyber security to name a few. In these applications, it is difficult or unfeasible to develop conventional algorithms to perform the needed tasks.[3][4] Since the focus of this book is on ML and its applications, we devote Chapter
参考来源
- 位置:《Machine Learning Fundamentals: Concepts, Models, and Applications》第01章《数据科学与机器学习概览》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Machine Learning Fundamentals: Concepts, Models, and Applications/_epub-src/OEBPS/xhtml/12_chapter01.xhtml)
- 结论依据:摘录中关于学习适合规则难显式表达的任务的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。
- 原始内容:ML algorithms are used in a wide variety of applications, such as in engineering, medicine, email filtering, speech recognition, agriculture, computer vision, facial recognition, signal processing, and cyber security to name a few. In these applications, it is difficult or unfeasible to develop conventional algorithms to perform the needed tasks.[3][4] Since the focus of this book is on ML and its applications, we devote Chapter