Skip to main content
Data Science

Return to Question

clarity, added information theory tag
Source Link
timleathart
timleathart
  • 4k
  • 22
  • 35

Im new to Machine Learning , so please just dont blast me .

Im studingI'm studying the Gradient Descentgradient descent algorithm for single hidden layer algorithmneural networks. Suppose that iI have an initial dataset and then iI use the Mean Normalizationmean normalization in order to scale the features.

Why mathematically do the normalizatednormalized features carry the same information of the initial features  ?

Im new to Machine Learning , so please just dont blast me .

Im studing the Gradient Descent single layer algorithm. Suppose that i have an initial dataset and then i use the Mean Normalization in order to scale the features.

Why mathematically do the normalizated features carry the same information of the initial features  ?

I'm studying the gradient descent algorithm for single hidden layer neural networks. Suppose that I have an initial dataset and then I use mean normalization in order to scale the features.

Why mathematically do the normalized features carry the same information of the initial features?

Source Link
Poiera
Poiera
  • 451
  • 1
  • 5
  • 9

After a Feature Scaling do i have the same initial information?

Im new to Machine Learning , so please just dont blast me .

Im studing the Gradient Descent single layer algorithm. Suppose that i have an initial dataset and then i use the Mean Normalization in order to scale the features.

Why mathematically do the normalizated features carry the same information of the initial features ?