typos typos typos grrrr

doc/pub/NeuralNet/html/._NeuralNet-bs034.html

@@ -263,7 +263,7 @@ MathJax.Hub.Config({
 In case we employ the more general case given by the Softmax equation, we need to evaluate the derivative of the activation function with respect to the activation \( z_i^l \), that is we need
 $$
 \frac{\partial f(z_i^l)}{\partial w_{jk}^l} =
-\frac{\partial f(z_i^l)}{\partial z_j^l} \frac{\partial z_j^l}{\partial w_{jk}^l}= \frac{\partial f(z_i^l)}{\partial z_j^l}a_k^{l}.
+\frac{\partial f(z_i^l)}{\partial z_j^l} \frac{\partial z_j^l}{\partial w_{jk}^l}= \frac{\partial f(z_i^l)}{\partial z_j^l}a_k^{l-1}.
 $$
 
 For the Softmax function we have

doc/pub/NeuralNet/html/NeuralNet-reveal.html

@@ -1388,7 +1388,7 @@ In case we employ the more general case given by the Softmax equation, we need t
 <p>&nbsp;<br>
 $$
 \frac{\partial f(z_i^l)}{\partial w_{jk}^l} =
-\frac{\partial f(z_i^l)}{\partial z_j^l} \frac{\partial z_j^l}{\partial w_{jk}^l}= \frac{\partial f(z_i^l)}{\partial z_j^l}a_k^{l}.
+\frac{\partial f(z_i^l)}{\partial z_j^l} \frac{\partial z_j^l}{\partial w_{jk}^l}= \frac{\partial f(z_i^l)}{\partial z_j^l}a_k^{l-1}.
 $$
 <p>&nbsp;<br>
 

doc/pub/NeuralNet/html/NeuralNet-solarized.html

@@ -1321,7 +1321,7 @@ In case we use another activation function than the logistic one, we need to eva
 In case we employ the more general case given by the Softmax equation, we need to evaluate the derivative of the activation function with respect to the activation \( z_i^l \), that is we need
 $$
 \frac{\partial f(z_i^l)}{\partial w_{jk}^l} =
-\frac{\partial f(z_i^l)}{\partial z_j^l} \frac{\partial z_j^l}{\partial w_{jk}^l}= \frac{\partial f(z_i^l)}{\partial z_j^l}a_k^{l}.
+\frac{\partial f(z_i^l)}{\partial z_j^l} \frac{\partial z_j^l}{\partial w_{jk}^l}= \frac{\partial f(z_i^l)}{\partial z_j^l}a_k^{l-1}.
 $$
 
 For the Softmax function we have

doc/pub/NeuralNet/html/NeuralNet.html

@@ -1326,7 +1326,7 @@ In case we use another activation function than the logistic one, we need to eva
 In case we employ the more general case given by the Softmax equation, we need to evaluate the derivative of the activation function with respect to the activation \( z_i^l \), that is we need
 $$
 \frac{\partial f(z_i^l)}{\partial w_{jk}^l} =
-\frac{\partial f(z_i^l)}{\partial z_j^l} \frac{\partial z_j^l}{\partial w_{jk}^l}= \frac{\partial f(z_i^l)}{\partial z_j^l}a_k^{l}.
+\frac{\partial f(z_i^l)}{\partial z_j^l} \frac{\partial z_j^l}{\partial w_{jk}^l}= \frac{\partial f(z_i^l)}{\partial z_j^l}a_k^{l-1}.
 $$
 
 For the Softmax function we have

doc/pub/NeuralNet/ipynb/NeuralNet.ipynb

@@ -1586,7 +1586,7 @@
    "source": [
     "$$\n",
     "\\frac{\\partial f(z_i^l)}{\\partial w_{jk}^l} =\n",
-    "\\frac{\\partial f(z_i^l)}{\\partial z_j^l} \\frac{\\partial z_j^l}{\\partial w_{jk}^l}= \\frac{\\partial f(z_i^l)}{\\partial z_j^l}a_k^{l}.\n",
+    "\\frac{\\partial f(z_i^l)}{\\partial z_j^l} \\frac{\\partial z_j^l}{\\partial w_{jk}^l}= \\frac{\\partial f(z_i^l)}{\\partial z_j^l}a_k^{l-1}.\n",
     "$$"
    ]
   },

doc/src/NeuralNet/NeuralNet.do.txt

@@ -1013,7 +1013,7 @@ In case we employ the more general case given by the Softmax equation, we need t
 !bt
 \[
 \frac{\partial f(z_i^l)}{\partial w_{jk}^l} =
-\frac{\partial f(z_i^l)}{\partial z_j^l} \frac{\partial z_j^l}{\partial w_{jk}^l}= \frac{\partial f(z_i^l)}{\partial z_j^l}a_k^{l}.
+\frac{\partial f(z_i^l)}{\partial z_j^l} \frac{\partial z_j^l}{\partial w_{jk}^l}= \frac{\partial f(z_i^l)}{\partial z_j^l}a_k^{l-1}.
 \]
 !et
 For the Softmax function we have