← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 6686.c · 生成模型:GPT-6

逻辑函数斜率偏移与增益分开

理解等级:中级

示例gain/(1+exp(−w(x−phase)))中,phase移动转折中心,w影响方向及陡峭度,gain缩放输出。其截距相当于−w·phase,而非phase本身;gain为1时中心导数为w/4,不是直接等于w。

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

      >>> def logistic(x, w=1., phase=0, gain=1): ... return gain / (1. + np.exp(-w * (x - phase))) And here is what a logistic function looks like and how the coefficient (weight) and phase (intercept) affect its shape: >>> import pandas as pd >>> import numpy as np >>> import seaborn as sns >>> sns.set_style() >>> xy = pd.DataFrame(np.arange(-50, 50) / 10., columns=['x']) >>> for w,

    参考来源

    - 位置:《Natural Language Processing in Action, Second Edition》第05章《神经网络基础》(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-5.html) - 结论依据:摘录中关于逻辑函数斜率偏移与增益分开的定义、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:>>> def logistic(x, w=1., phase=0, gain=1): ... return gain / (1. + np.exp(-w * (x - phase))) And here is what a logistic function looks like and how the coefficient (weight) and phase (intercept) affect its shape: >>> import pandas as pd >>> import numpy as np >>> import seaborn as sns >>> sns.set_style() >>> xy = pd.DataFrame(np.arange(-50, 50) / 10., columns=['x']) >>> for w,