Differences

This shows you the differences between two versions of the page.

Link to this comparison view

dimensionless_features [2016/07/12 21:07] (current)
Line 1: Line 1:
 +See Batch Normalization. ​ The measures that serve as input to the classifiers are ideally dimensionless dues to normalization. ​
  
 +**References**
 +
 +http://​timvieira.github.io/​blog/​post/​2016/​05/​27/​dimensional-analysis-of-gradient-ascent
 +
 +https://​en.wikipedia.org/​wiki/​Mahalanobis_distance
 +
 +https://​en.wikipedia.org/​wiki/​Nondimensionalization
 +
 +https://​en.wikipedia.org/​wiki/​Normalization_(statistics)