typo in neural net

doc/pub/NeuralNet/html/._NeuralNet-bs061.html

@@ -268,7 +268,7 @@ since the gradient of the ReLU function is 0 when its input is negative.
 <p>
 To solve this problem, you may want to use a variant of the ReLU function, such as the leaky ReLU discussed before or the so-called exponential linear unit (ELU) function
 $$
-ELU(z) = \left\{\begin{array}{cc} \alpha\left( \exp{(z)}-1\right) & z > 0,\\  z & z \le 0.\end{array}\right. 
+ELU(z) = \left\{\begin{array}{cc} \alpha\left( \exp{(z)}-1\right) & z < 0,\\  z & z \ge 0.\end{array}\right. 
 $$
 
 <p>

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

@@ -2873,7 +2873,7 @@ since the gradient of the ReLU function is 0 when its input is negative.
 To solve this problem, you may want to use a variant of the ReLU function, such as the leaky ReLU discussed before or the so-called exponential linear unit (ELU) function
 <p>&nbsp;<br>
 $$
-ELU(z) = \left\{\begin{array}{cc} \alpha\left( \exp{(z)}-1\right) & z > 0,\\  z & z \le 0.\end{array}\right. 
+ELU(z) = \left\{\begin{array}{cc} \alpha\left( \exp{(z)}-1\right) & z < 0,\\  z & z \ge 0.\end{array}\right. 
 $$
 <p>&nbsp;<br>
 

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

@@ -2731,7 +2731,7 @@ since the gradient of the ReLU function is 0 when its input is negative.
 <p>
 To solve this problem, you may want to use a variant of the ReLU function, such as the leaky ReLU discussed before or the so-called exponential linear unit (ELU) function
 $$
-ELU(z) = \left\{\begin{array}{cc} \alpha\left( \exp{(z)}-1\right) & z > 0,\\  z & z \le 0.\end{array}\right. 
+ELU(z) = \left\{\begin{array}{cc} \alpha\left( \exp{(z)}-1\right) & z < 0,\\  z & z \ge 0.\end{array}\right. 
 $$
 
 <p>

doc/pub/NeuralNet/html/NeuralNet.html

@@ -2736,7 +2736,7 @@ since the gradient of the ReLU function is 0 when its input is negative.
 <p>
 To solve this problem, you may want to use a variant of the ReLU function, such as the leaky ReLU discussed before or the so-called exponential linear unit (ELU) function
 $$
-ELU(z) = \left\{\begin{array}{cc} \alpha\left( \exp{(z)}-1\right) & z > 0,\\  z & z \le 0.\end{array}\right. 
+ELU(z) = \left\{\begin{array}{cc} \alpha\left( \exp{(z)}-1\right) & z < 0,\\  z & z \ge 0.\end{array}\right. 
 $$
 
 <p>

doc/pub/NeuralNet/ipynb/NeuralNet.ipynb

@@ -3021,7 +3021,7 @@
    "metadata": {},
    "source": [
     "$$\n",
-    "ELU(z) = \\left\\{\\begin{array}{cc} \\alpha\\left( \\exp{(z)}-1\\right) & z > 0,\\\\  z & z \\le 0.\\end{array}\\right.\n",
+    "ELU(z) = \\left\\{\\begin{array}{cc} \\alpha\\left( \\exp{(z)}-1\\right) & z < 0,\\\\  z & z \\ge 0.\\end{array}\\right.\n",
     "$$"
    ]
   },

doc/src/NeuralNet/NeuralNet.do.txt

@@ -2263,7 +2263,7 @@ since the gradient of the ReLU function is 0 when its input is negative.
 To solve this problem, you may want to use a variant of the ReLU function, such as the leaky ReLU discussed before or the so-called exponential linear unit (ELU) function
 !bt
 \[
-ELU(z) = \left\{\begin{array}{cc} \alpha\left( \exp{(z)}-1\right) & z > 0,\\  z & z \le 0.\end{array}\right. 
+ELU(z) = \left\{\begin{array}{cc} \alpha\left( \exp{(z)}-1\right) & z < 0,\\  z & z \ge 0.\end{array}\right. 
 \]
 !et