# 可视化自编码器训练结果

 Revision as of 10:42, 7 March 2013 (view source)Kandeng (Talk | contribs)← Older edit Revision as of 10:44, 7 March 2013 (view source)Kandeng (Talk | contribs) Newer edit → Line 1: Line 1: 可视化自编码器训练结果 可视化自编码器训练结果 【原文】： 【原文】： - Having trained a (sparse) autoencoder, we would now like to visualize the function learned by the algorithm, to try to understand what it has learned. Consider the case of training an autoencoder on [[File:http://deeplearning.stanford.edu/wiki/images/math/0/4/a/04aaf6cd0499a40a7c222ffdb85b55bb.png]] images, so that . Each hidden unit   computes a function of the input: + Having trained a (sparse) autoencoder, we would now like to visualize the function + learned by the algorithm, to try to understand what it has learned. + Consider the case of training an autoencoder on $\textstyle 10 \times 10 images, so that [itex]\textstyle n = 100$. + Each hidden unit $\textstyle i$ computes a function of the input: 【初译】： 【初译】： 得到了训练好的（稀疏）自编码器，我们就可以将通过算法习得的函数进行可视化，以便于了解学习的结果。我们以使用10×10的图像来训练自编码器为例，此时n=100。针对每个隐藏单元i，将输入值代入以下方程： 得到了训练好的（稀疏）自编码器，我们就可以将通过算法习得的函数进行可视化，以便于了解学习的结果。我们以使用10×10的图像来训练自编码器为例，此时n=100。针对每个隐藏单元i，将输入值代入以下方程：