Rain-Bus/Obsidian
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Compare commits

base: Rain-Bus:072605d1fffb90c7e7a306b5b8fea6bec109198e
Branches Tags
Rain-Bus:main
...
compare: Rain-Bus:eac6ddd7461e4ae1a0486a410a2f7eb1d09de8c2
Branches Tags
Rain-Bus:main

3 Commits
072605d1ff ... eac6ddd746

Author SHA1 Message Date
RainBus
eac6ddd746 vault backup: 2023-10-23 20:39:28 2023-10-23 20:39:29 +08:00
RainBus
8af0c88db0 vault backup: 2023-10-17 16:14:14 2023-10-17 16:14:14 +08:00
RainBus
114c85c1b0 vault backup: 2023-10-17 15:59:24 2023-10-17 15:59:25 +08:00
2 changed files with 9 additions and 2 deletions
Expand all files Collapse all files

2
.obsidian/appearance.json vendored
View File

@@ -2,7 +2,7 @@
"accentColor": "", "accentColor": "",
"cssTheme": "Minimal", "cssTheme": "Minimal",
"monospaceFontFamily": "Maple Mono SC NF", "monospaceFontFamily": "Maple Mono SC NF",
"theme": "moonstone", "theme": "obsidian",
"interfaceFontFamily": "霞鹜文楷", "interfaceFontFamily": "霞鹜文楷",
"textFontFamily": "霞鹜文楷等宽", "textFontFamily": "霞鹜文楷等宽",
"translucency": false "translucency": false

9
Study/DL/吴恩达深度学习课程/Lesson 1.md
View File

@@ -15,4 +15,11 @@ w &= w - \eta \cdot dw \\
b &= b - \eta \cdot db b &= b - \eta \cdot db
\end{align}$$ \end{align}$$
正向传递：计算网络输出。 正向传递：计算网络输出。
反向传递：更新模型参数。 反向传递：更新模型参数。
sigmoid函数：消除线性。
> 线性激活函数: $a = z$
> 如果我们使用线性激活函数，无论我们经过多少层网络迭代，都相当于是对输入进行线性变换。
损失函数：计算模型预测结果的精度，反向传播的目的就是使得。
## Vectorization
向量化相较于显式循环更高效，能够更好的利用系统的并行化计算。