知识卡片
学习模型需要目标场景证据
缺少足够第一性模型时,可从数据学习传感到状态或控制的关系。表达能力强不证明有限数据和训练能学到正确行为,也不能从训练准确率推出可解释性或所有环境可靠性;模型选择应结合先验、数据覆盖与验证需求。
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
- · 人工神经网络
原书出处 · 1 处
- · 查看原书依据
Machine learning is a large field that shares many of its foundations with robotics, in particular concerning probability theory and statistics. Deep learning may be used as a drop-in replacement for sensor preprocessing and conditioning, computer vision and feature extraction, and localization; it may even replace controllers for locomotion and grasping. For each of these applications, it is important to understand when deep learning may
参考来源
- 位置:《Introduction to Autonomous Robots Mechanisms, Sensors, Actuators, and Algorithms (Nikolaus Correll, Bradley Hayes etc.)》第10章《人工神经网络》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Introduction to Autonomous Robots Mechanisms, Sensors, Actuators, and Algorithms (Nikolaus Correll, Bradley Hayes etc.)/_epub-src/OEBPS/xhtml/chapter_10.xhtml)
- 结论依据:摘录中关于学习模型需要目标场景证据的定义、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:Machine learning is a large field that shares many of its foundations with robotics, in particular concerning probability theory and statistics. Deep learning may be used as a drop-in replacement for sensor preprocessing and conditioning, computer vision and feature extraction, and localization; it may even replace controllers for locomotion and grasping. For each of these applications, it is important to understand when deep learning may