Data Normalization

[!def] Normalization
Normalization is the process of transforming raw values to standard range of values, typically [0, 1] or [-1, 1]
$$
\bar{x} = \frac{x_i - min}{max - min}
$$

[!question] Why Normalization?

• It increases learning speed; hence fast convergence
• If no normalization, then big numeric features dominate the learning