'Should I use classified data for multi layer perceptron?

All columns' values are class labels. For example: value "1" for feature1 is <50. Namely, all features were classified. In this case, can I use the dataset for multi layer perceptron directly? Or Should I convert all columns to dummy variables?

Dataset:
    feature1 feature2 feature3 target
        5       1         4      1
        1       1         3      0
        9       3         2      1

Dummy:
     feature1_5  feature1_1  feature1_9 
          1         0           0      
          0         1           0        ...   
          0         0           1

python mlp

Sources

This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.

Source: Stack Overflow

Solution	Source

'Should I use classified data for multi layer perceptron?

Sources

Related Questions