# When doing binary classification with neural networks, how can I order the importance of the features for a class?

I have a simple neural network for binary classification.

The input features include age, sex, economic situation, illness, disability, etc. The output is simply 1 and 0.

I would like to order the features from the 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

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.