知识卡片

普通读书笔记卡 · 6713.c · 生成模型:GPT-6

互相关不同于皮尔逊系数

理解等级:中级

CNN常用不翻转核的滑动加权和,数学上属于互相关;皮尔逊相关还需减均值并按方差归一。二者都可探索模式,但数值范围、尺度敏感性和常量输入处理不同,不能把普通卷积输出都叫相关系数。

这张卡片看不懂?

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

      7.2.3 Correlation vs. convolution In case you’ve forgotten, the following listing should remind you what correlation looks like in Python (or you can use scipy.stats.pearsonr). Listing 7.1 A function to compute Pierson correlation >>> import numpy as np >>> def corr(a, b): ... """ Compute the Pearson correlation coefficient R """ ... a = a - np.mean(a) ... b = b - np.mean(b) ... return

    参考来源

    - 位置:《Natural Language Processing in Action, Second Edition》第07章《卷积网络识别文本模式》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Natural Language Processing in Action, Second Edition/_epub-src/OEBPS/Text/chapter-7.html) - 结论依据:摘录中关于互相关不同于皮尔逊系数的定义、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:7.2.3 Correlation vs. convolution In case you’ve forgotten, the following listing should remind you what correlation looks like in Python (or you can use scipy.stats.pearsonr). Listing 7.1 A function to compute Pierson correlation >>> import numpy as np >>> def corr(a, b): ... """ Compute the Pearson correlation coefficient R """ ... a = a - np.mean(a) ... b = b - np.mean(b) ... return