Obtain the most important input data for binary classification on a neural network

Question

I have a simple neural network for binary classification.
Input features into this network include: age, sex, economic_situation, illness, disability, etc.
and the output is simply 1 and 0

I would like to order the features for each input from greatest to least impact it had on the classification

An example answer could look like this:

Classification: 1
1) illness
2) economic_situation
3) disability
4) sex
5) age

Another example:

Classification: 0 
1) economic_situation
2) age
3) disability
4) sex
5) illness

Thank you very much

Answer 1

Two popular methods I’ve seen done:

1) For each feature, remove it and run the model and see the impact it has on the result. The idea is that the larger the impact, the more pertinent it was to the result.

2) Look at the gradients magnitude $|\nabla_f {y} |$. You can either look at the raw gradient or look at the guided back-propagation which is just the back props product rule, but you only look at when the nodes positively help trigger a neuron by taking only the positive gradients at each step.

There’s probably also more methods. Hope this helped.