数据预处理

From Ufldl

Jump to: navigation, search
Line 133: Line 133:
[[File:ZCA_Eigenvalues_Plot.png]]
[[File:ZCA_Eigenvalues_Plot.png]]
 +
【原文】
【原文】
In reconstruction based models, the loss function includes a term that penalizes reconstructions that are far from the original inputs. Then, if <tt>epsilon</tt> is set too ''low'', the data will contain a lot of noise which the model will need to reconstruct well. As a result, it is very important for reconstruction based models to have data that has been low-pass filtered.
In reconstruction based models, the loss function includes a term that penalizes reconstructions that are far from the original inputs. Then, if <tt>epsilon</tt> is set too ''low'', the data will contain a lot of noise which the model will need to reconstruct well. As a result, it is very important for reconstruction based models to have data that has been low-pass filtered.

Revision as of 10:06, 9 March 2013

Personal tools