Fixing latex in all translations

docs/es/week01/01-1.md

@@ -105,25 +105,25 @@ La forma más eficiente se llama Descenso de Gradiente Estocástico (SGD). Dado
 
 ### [Cálculo de gradientes por retropropagación](https://www.youtube.com/watch?v=0bMe_vCZo30&t=2336s)
 
-<!-- Computing gradients by backpropagation is a practical application of the chain rule. The backpropagation for state gradients is as follows:
+<!-- Computing gradients by backpropagation is a practical application of the chain rule. The backpropagation equation for the input gradients is as follows:
 -->
 Calcular gradientes por retropropagación es una aplicación práctica de la regla de la cadena. La propagación hacia atrás para los gradientes del estado es la siguiente:
 
 $$
 \begin{aligned}
-\frac{\partial C}{\partial X_{i - 1}} &= \frac{\partial C}{\partial X_i}\frac{\partial X_i}{\partial X_{i - 1}} \\
-\frac{\partial C}{\partial X_{i - 1}} &= \frac{\partial C}{\partial X_i}\frac{\partial F_i(X_{i - 1}, W_i)}{\partial X_{i - 1}}
+\frac{\partial C}{\partial \boldsymbol{x}_{i - 1}} &= \frac{\partial C}{\partial \boldsymbol{x}_i}\frac{\partial \boldsymbol{x}_i}{\partial \boldsymbol{x}_{i - 1}} \\
+\frac{\partial C}{\partial \boldsymbol{x}_{i - 1}} &= \frac{\partial C}{\partial \boldsymbol{x}_i}\frac{\partial f_i(\boldsymbol{x}_{i - 1}, \boldsymbol{w}_i)}{\partial \boldsymbol{x}_{i - 1}}
 \end{aligned}
 $$
 
-<!-- The backpropagation for weight gradients is as follows:
+<!-- The backpropagation equation for the weight gradients is as follows:
 -->
 La propagación hacia atrás para los gradientes de los pesos es:
 
 $$
 \begin{aligned}
-\frac{\partial C}{\partial W_{i}} &= \frac{\partial C}{\partial X_i}\frac{\partial X_i}{\partial W_{i}} \\
-\frac{\partial C}{\partial W_{i}} &= \frac{\partial C}{\partial X_i}\frac{\partial F_i(X_{i - 1}, W_i)}{\partial W_{i}}
+\frac{\partial C}{\partial \boldsymbol{w}_{i}} &= \frac{\partial C}{\partial \boldsymbol{x}_i}\frac{\partial \boldsymbol{x}_i}{\partial \boldsymbol{w}_{i}} \\
+\frac{\partial C}{\partial \boldsymbol{w}_{i}} &= \frac{\partial C}{\partial \boldsymbol{x}_i}\frac{\partial f_i(\boldsymbol{x}_{i - 1}, \boldsymbol{w}_i)}{\partial \boldsymbol{w}_{i}}
 \end{aligned}
 $$
 

docs/ko/week01/01-1.md

@@ -66,17 +66,17 @@ translator: Gio
 
 $$
 \begin{aligned}
-\frac{\partial C}{\partial X_{i - 1}} &= \frac{\partial C}{\partial X_i}\frac{\partial X_i}{\partial X_{i - 1}} \\
-\frac{\partial C}{\partial X_{i - 1}} &= \frac{\partial C}{\partial X_i}\frac{\partial F_i(X_{i - 1}, W_i)}{\partial X_{i - 1}}
+\frac{\partial C}{\partial \boldsymbol{x}_{i - 1}} &= \frac{\partial C}{\partial \boldsymbol{x}_i}\frac{\partial \boldsymbol{x}_i}{\partial \boldsymbol{x}_{i - 1}} \\
+\frac{\partial C}{\partial \boldsymbol{x}_{i - 1}} &= \frac{\partial C}{\partial \boldsymbol{x}_i}\frac{\partial f_i(\boldsymbol{x}_{i - 1}, \boldsymbol{w}_i)}{\partial \boldsymbol{x}_{i - 1}}
 \end{aligned}
 $$
 
 가중치 경사에 대한 역전파는 다음과 같다:
 
 $$
 \begin{aligned}
-\frac{\partial C}{\partial W_{i}} &= \frac{\partial C}{\partial X_i}\frac{\partial X_i}{\partial W_{i}} \\
-\frac{\partial C}{\partial W_{i}} &= \frac{\partial C}{\partial X_i}\frac{\partial F_i(X_{i - 1}, W_i)}{\partial W_{i}}
+\frac{\partial C}{\partial \boldsymbol{w}_{i}} &= \frac{\partial C}{\partial \boldsymbol{x}_i}\frac{\partial \boldsymbol{x}_i}{\partial \boldsymbol{w}_{i}} \\
+\frac{\partial C}{\partial \boldsymbol{w}_{i}} &= \frac{\partial C}{\partial \boldsymbol{x}_i}\frac{\partial f_i(\boldsymbol{x}_{i - 1}, \boldsymbol{w}_i)}{\partial \boldsymbol{w}_{i}}
 \end{aligned}
 $$
 

docs/zh/week01/01-1.md

@@ -67,17 +67,17 @@ $90\%$的深度学习应用使用监督学习。监督学习中，你需要收
 
 $$
 \begin{aligned}
-\frac{\partial C}{\partial X_{i - 1}} &= \frac{\partial C}{\partial X_i}\frac{\partial X_i}{\partial X_{i - 1}} \\
-\frac{\partial C}{\partial X_{i - 1}} &= \frac{\partial C}{\partial X_i}\frac{\partial F_i(X_{i - 1}, W_i)}{\partial X_{i - 1}}
+\frac{\partial C}{\partial \boldsymbol{x}_{i - 1}} &= \frac{\partial C}{\partial \boldsymbol{x}_i}\frac{\partial \boldsymbol{x}_i}{\partial \boldsymbol{x}_{i - 1}} \\
+\frac{\partial C}{\partial \boldsymbol{x}_{i - 1}} &= \frac{\partial C}{\partial \boldsymbol{x}_i}\frac{\partial f_i(\boldsymbol{x}_{i - 1}, \boldsymbol{w}_i)}{\partial \boldsymbol{x}_{i - 1}}
 \end{aligned}
 $$
 
 权重梯度的反向传播（计算）如下：
 
 $$
 \begin{aligned}
-\frac{\partial C}{\partial W_{i}} &= \frac{\partial C}{\partial X_i}\frac{\partial X_i}{\partial W_{i}} \\
-\frac{\partial C}{\partial W_{i}} &= \frac{\partial C}{\partial X_i}\frac{\partial F_i(X_{i - 1}, W_i)}{\partial W_{i}}
+\frac{\partial C}{\partial \boldsymbol{w}_{i}} &= \frac{\partial C}{\partial \boldsymbol{x}_i}\frac{\partial \boldsymbol{x}_i}{\partial \boldsymbol{w}_{i}} \\
+\frac{\partial C}{\partial \boldsymbol{w}_{i}} &= \frac{\partial C}{\partial \boldsymbol{x}_i}\frac{\partial f_i(\boldsymbol{x}_{i - 1}, \boldsymbol{w}_i)}{\partial \boldsymbol{w}_{i}}
 \end{aligned}
 $$