知识卡片
矩阵乘法按内轴匹配外轴输出
A为m×n、B为n×p时,AB为m×p,输出每项是A一行与B一列的点积。形状可乘仍需核对轴的业务含义,换顺序通常不相等;不能因为都有相同元素就把转置视为无关操作。
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
原书出处 · 1 处
- · 查看原书依据
Matrix multiplication is an operation that takes two matrices and produces another matrix. For two matrices to be multiplied, the number of columns in the first matrix must equal the number of rows in the second matrix. For matrices A (size m × n) and B (size n × p), the product AB is an m × p matrix. Each element of the resulting matrix
参考来源
- 位置:《Natural Language Processing in Action, Second Edition》附录C《附录C:向量与线性代数》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Natural Language Processing in Action, Second Edition/_epub-src/OEBPS/Text/appendix-c.html)
- 结论依据:摘录中关于矩阵乘法按内轴匹配外轴输出的定义、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:Matrix multiplication is an operation that takes two matrices and produces another matrix. For two matrices to be multiplied, the number of columns in the first matrix must equal the number of rows in the second matrix. For matrices A (size m × n) and B (size n × p), the product AB is an m × p matrix. Each element of the resulting matrix