知识卡片
训练与推理汇总不同尺度数据
常规训练将整个数据集经过优化汇总到参数,前向推理再将一个输入转换为激活。原书用慢参数与快激活表达这种时间尺度差异,并非规定所有系统推理时绝不能适应参数。分清两条路径有助追踪某个输出利用了哪些数据。
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
- · 神经网络
原书出处 · 1 处
- · 查看原书依据
Parameters are also functions of the data (they are learned from data) but they are slow functions of datasets: the parameters are arrived at via an optimization procedure over a whole dataset. So, both activations and parameters are statistics of the data, that is, information extracted about about the data that organizes or summarizes it. The parameters are a kind of metasummary since they specify
参考来源
- 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第12章《神经网络》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)/_epub-src/OPS/xhtml/c012.xhtml)
- 结论依据:摘录中关于训练与推理汇总不同尺度数据的定义、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:Parameters are also functions of the data (they are learned from data) but they are slow functions of datasets: the parameters are arrived at via an optimization procedure over a whole dataset. So, both activations and parameters are statistics of the data, that is, information extracted about about the data that organizes or summarizes it. The parameters are a kind of metasummary since they specify