Neural Networks

From Ufldl

Jump to: navigation, search
 
Line 31: Line 31:
-
 
+
<div align=center>
-
[[Image:Sigmoid_Function.png|400px|center|Sigmoid activation function.]]
+
[[Image:Sigmoid_Function.png|400px|top|Sigmoid activation function.]]
-
[[Image:Tanh_Function.png|400px|center|Tanh activation function.]]
+
[[Image:Tanh_Function.png|400px|top|Tanh activation function.]]
 +
</div>
The <math>\tanh(z)</math> function is a rescaled version of the sigmoid, and its output range is
The <math>\tanh(z)</math> function is a rescaled version of the sigmoid, and its output range is
<math>[-1,1]</math> instead of <math>[0,1]</math>.
<math>[-1,1]</math> instead of <math>[0,1]</math>.
-
Note that unlike CS221 and (parts of) CS229, we are not using the convention
+
Note that unlike some other venues (including the OpenClassroom videos, and parts of CS229), we are not using the convention
here of <math>x_0=1</math>.  Instead, the intercept term is handled separately by the parameter <math>b</math>.
here of <math>x_0=1</math>.  Instead, the intercept term is handled separately by the parameter <math>b</math>.
Line 128: Line 129:
example of a '''feedforward''' neural network, since the connectivity graph
example of a '''feedforward''' neural network, since the connectivity graph
does not have any directed loops or cycles.
does not have any directed loops or cycles.
-
%We will write <math>\textstyle s_l</math> to denote the
 
-
%number of units in layer <math>\textstyle l</math> of the network (not counting the bias unit).
 
Line 143: Line 142:
patient, and the different outputs <math>y_i</math>'s might indicate presence or absence
patient, and the different outputs <math>y_i</math>'s might indicate presence or absence
of different diseases.)
of different diseases.)
 +
 +
 +
{{Sparse_Autoencoder}}
 +
 +
 +
{{Languages|神经网络|中文}}

Latest revision as of 19:38, 6 April 2013

Personal tools