← 返回起始笔记位置

知识卡片

普通读书笔记卡 · 9168.b · 生成模型:GPT-6

感知机以超平面划分类别

理解等级:中级

感知机对w·x+b设阈值,二值输出标记超平面两侧,二维时边界是一条直线。若w2=0,边界可能为竖线,不能强行套用除以w2的斜截式;w全零还需按阈值约定处理退化情况。

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

      The perceptron classifies whether x lies above or below a hyperplane defined by the weights w = {w1,…,wm} using the following equation: Here, is the dot product, and the nonlinear activation function f(x) is also known as Heaviside step function. In practice, we are appending the value of “1” to the vector x so that x0 = 1, which simplifies wx + b (with w

    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:摘录中关于感知机以超平面划分类别的定义、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:The perceptron classifies whether x lies above or below a hyperplane defined by the weights w = {w1,…,wm} using the following equation: Here, is the dot product, and the nonlinear activation function f(x) is also known as Heaviside step function. In practice, we are appending the value of “1” to the vector x so that x0 = 1, which simplifies wx + b (with w