Saliency maps of neural networks (using Keras)

Question

I have a fully connected multilayer perceptron trained in Keras. I feed it an N-dimensional feature vector and it predicts one out of M classes for the input vector. The trainin

Answer 1

I found the solution:

    get_output = theano.function([model.layers[0].input],model.layers[-1].output,allow_input_downcast=True)
    fx = theano.function( [model.layers[0].input] ,T.jacobian(model.layers[-1].output.flatten(),model.layers[0].input), allow_input_downcast=True)
    grad = fx([input_feature])