In classification app, which standardization method is used for neural networks?

In classification app, when you choose a neural network method, you can choose whether or not to standardize the data like the picture below shows. However, which standardization method does the app use?

Answer 1

[MathWorks Support Team]

As you can see first in the official document "Choose Classifier Options" (link), you can see that the "fitcnet" function is used when performing classification using a neural network. In addition, fitcnet explains the "Standardize" option as follows, so you can see that normalization is performed using the mean and standard deviation.

Flag to standardize the predictor data, specified as a numeric or logical 0 (false) or 1 (true). If you set Standardize to true, then the software centers and scales each numeric predictor variable by the corresponding column mean and standard deviation. The software does not standardize the categorical predictors.

- fitcnet

https://www.mathworks.com/help/releases/R2022b/stats/fitcnet.html#namevaluepairarguments