Deploy to GitHub Pages: c1ae3396

develop/doc/_sources/howto/dev/new_layer_en.rst.txt

@@ -37,7 +37,7 @@ Suppose our loss function is :math:`c(y)`, then
 
    \frac{\partial c(y)}{\partial x} = \frac{\partial c(y)}{\partial y} \frac{\partial y}{\partial x}
 
-Suppose :math:`z = f(W^T x + b)`, then
+Suppose :math:`z = W^T x + b`, then
 
 .. math::
 

develop/doc/howto/dev/new_layer_en.html

@@ -207,7 +207,7 @@ Fully connected layer takes a dense input vector with dimension <span class="mat
 <p>Suppose our loss function is <span class="math">\(c(y)\)</span>, then</p>
 <div class="math">
 \[\frac{\partial c(y)}{\partial x} = \frac{\partial c(y)}{\partial y} \frac{\partial y}{\partial x}\]</div>
-<p>Suppose <span class="math">\(z = f(W^T x + b)\)</span>, then</p>
+<p>Suppose <span class="math">\(z = W^T x + b\)</span>, then</p>
 <div class="math">
 \[\frac{\partial y}{\partial z} = \frac{\partial f(z)}{\partial z}\]</div>
 <p>This derivative can be automatically computed by our base layer class.</p>

develop/doc_cn/_sources/howto/dev/new_layer_cn.rst.txt

@@ -37,7 +37,7 @@
 
    \frac{\partial c(y)}{\partial x} = \frac{\partial c(y)}{\partial y} \frac{\partial y}{\partial x}
 
-假设 :math:`z = f(W^T x + b)` ，那么
+假设 :math:`z = W^T x + b` ，那么
 
 .. math::
 

develop/doc_cn/howto/dev/new_layer_cn.html

@@ -207,7 +207,7 @@
 <p>假设损失函数是 <span class="math">\(c(y)\)</span> ，那么</p>
 <div class="math">
 \[\frac{\partial c(y)}{\partial x} = \frac{\partial c(y)}{\partial y} \frac{\partial y}{\partial x}\]</div>
-<p>假设 <span class="math">\(z = f(W^T x + b)\)</span> ，那么</p>
+<p>假设 <span class="math">\(z = W^T x + b\)</span> ，那么</p>
 <div class="math">
 \[\frac{\partial y}{\partial z} = \frac{\partial f(z)}{\partial z}\]</div>
 <p>PaddlePaddle的base layer类可以自动计算上面的导数。</p>