Linear Decoders
From Ufldl
(→Sparse Autoencoder Recap) |
(→Sparse Autoencoder Recap) |
||
Line 80: | Line 80: | ||
While some datasets like MNIST fit well with this scaling of the output, this can sometimes be awkward to satisfy. For example, if one uses PCA whitening, the input is | While some datasets like MNIST fit well with this scaling of the output, this can sometimes be awkward to satisfy. For example, if one uses PCA whitening, the input is | ||
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 == |