Linear Decoders

From Ufldl

Jump to: navigation, search
(Sparse Autoencoder Recap)
 
Line 1: Line 1:
-
【原文】:
 
== Sparse Autoencoder Recap ==
== Sparse Autoencoder Recap ==
-
 
-
【初译】:
 
-
 
-
稀疏自编码重述
 
-
 
-
【一校】:
 
-
 
-
稀疏自编码重述
 
-
 
-
【原文】:
 
In the sparse autoencoder, we had 3 layers of neurons: an input layer, a hidden layer and an output layer.  In our previous description
In the sparse autoencoder, we had 3 layers of neurons: an input layer, a hidden layer and an output layer.  In our previous description
Line 16: Line 5:
In these notes, we describe a modified version of the autoencoder in which some of the neurons use a different activation function.
In these notes, we describe a modified version of the autoencoder in which some of the neurons use a different activation function.
This will result in a model that is sometimes simpler to apply, and can also be more robust to variations in the parameters.  
This will result in a model that is sometimes simpler to apply, and can also be more robust to variations in the parameters.  
-
 
-
【初译】:
 
-
 
-
在稀疏自编码中,有三层:输入层,隐含层和输出层。在之前对自编码的定义(在神经网络中),位于神经网络中的每个神经元采用相同激励机制。在这些记录中,我们描述了一个修改版的自编码,其中一些神经元采用另外的激励机制。这产生一个更简易于应用,针对参数变化稳健性更佳的模型。
 
-
 
-
【一校】:
 
-
 
-
稀疏自编码器包含3层神经元,分别是输入层,隐含层以及输出层。
 
-
从前面(神经网络)自编码器描述可知,位于神经网络中的神经元都采用相同的激励函数。
 
-
在注解中,我们修改了自编码器定义,使得某些神经元采用不同的激励函数。这样得到的模型更容易应用,而且模型对参数的变化也更为鲁棒。
 
-
 
-
【原文】:
 
Recall that each neuron (in the output layer) computed the following:
Recall that each neuron (in the output layer) computed the following:
Line 39: Line 16:
where <math>a^{(3)}</math> is the output.  In the autoencoder, <math>a^{(3)}</math> is our approximate reconstruction of the input <math>x = a^{(1)}</math>.  
where <math>a^{(3)}</math> is the output.  In the autoencoder, <math>a^{(3)}</math> is our approximate reconstruction of the input <math>x = a^{(1)}</math>.  
-
 
-
【初译】:
 
-
 
-
每一个神经元(输出层)计算方式如下:
 
-
 
-
<math>
 
-
\begin{align}
 
-
z^{(3)} &= W^{(2)} a^{(2)} + b^{(2)} \\
 
-
a^{(3)} &= f(z^{(3)})
 
-
\end{align}
 
-
</math>
 
-
 
-
这里 <math>a^{(3)}</math> 是输出. 在自编码中, <math>a^{(3)}</math> 是对输入<math>x = a^{(1)}</math>的近似重建。
 
-
 
-
【一校】:
 
-
 
-
回想一下,输出层神经元计算公式如下:
 
-
 
-
<math>
 
-
\begin{align}
 
-
z^{(3)} &= W^{(2)} a^{(2)} + b^{(2)} \\
 
-
a^{(3)} &= f(z^{(3)})
 
-
\end{align}
 
-
</math>
 
-
 
-
其中 <math>a^{(3)}</math> 是输出. 在自编码器中, <math>a^{(3)}</math> 近似重构了输入<math>x = a^{(1)}</math>。
 
-
 
-
 
-
【原文】:
 
-
 
-
【初译】:
 
-
 
-
【一校】:
 
-
 
-
 
-
【原文】:
 
Because we used a sigmoid activation function for <math>f(z^{(3)})</math>, we needed to constrain or scale the inputs to be in the range <math>[0,1]</math>,  
Because we used a sigmoid activation function for <math>f(z^{(3)})</math>, we needed to constrain or scale the inputs to be in the range <math>[0,1]</math>,  
Line 81: Line 22:
no longer constrained to <math>[0,1]</math> and it's not clear what the best way is to scale the data to ensure it fits into the constrained range.
no longer constrained to <math>[0,1]</math> and it's not clear what the best way is to scale the data to ensure it fits into the constrained range.
-
【初译】:
 
-
 
-
对于 <math>f(z^{(3)})</math>采用一个S型激励函数后,因S型函数输出值域为 <math>[0,1]</math>,需限制输入的范围为 <math>[0,1]</math>。有一些数据组,例如MNIST手写数字库中其输入输出范围符合极佳,但这种情况难以满足。例如,若采用PCA白化,输入将不再限制于 <math>[0,1]</math>,虽可通过缩放数据来确保其符合特定范围内,显然,这不是最好的方式。
 
-
 
-
【一校】:
 
-
 
-
S型激励函数输出范围是<math>[0,1]</math>,当<math>f(z^{(3)})</math>采用该激励函数时,就要对输入限制或缩放,使其位于<math>[0,1]</math>范围中。一些数据集,比如MNIST,能方便将输出缩放到[0,1]中,但是在输入方面,很难满足要求。比如,PCA白化处理的输入并不满足<math>[0,1]</math>范围要求,也不清楚是否有最好的办法可以将数据缩放到特定范围中。
 
== Linear Decoder ==
== Linear Decoder ==
Line 127: Line 61:
Because the hidden layer is using a sigmoid (or tanh) activation <math>f</math>, in the equation above <math>f'(\cdot)</math> should still be the
Because the hidden layer is using a sigmoid (or tanh) activation <math>f</math>, in the equation above <math>f'(\cdot)</math> should still be the
derivative of the sigmoid (or tanh) function.
derivative of the sigmoid (or tanh) function.
 +
 +
 +
{{Languages|线性解码器|中文}}

Latest revision as of 04:06, 8 April 2013

Personal tools