I have a simple neural network in Keras with 16 inputs and 1 output. I want to be able to find out which of these inputs is the most important in determining the output (i.e. varying which input would affect the output the most). How can I do that in Keras or TensorFlow? I know I can dump the weights of the trained neural network into a file, but that won't help as the weights are just from one node to another in the next hidden layer.ThanksXtrain, Xtest, Ytrain, Ytest = train_test_split(X, Y, test_size=.5)model = Sequential()model.add(Dense(20, activation='relu', input_dim=16))model.add(Dense(10, activation='relu'))model.add(Dense(5, activation='relu'))model.add(Dense(1, activation='relu'))model.compile(loss='mse', optimizer='rmsprop')model.fit(Xtrain, Ytrain, validation_data=(Xtest,Ytest), epochs=200, batch_size=100, verbose=1)Ypred = model.predict(Xtest)

Adding weights per input (of connections to next layer) may be a start. Negative weights also signify influence.

**2019年06月19日20分35秒**

- How to determine a Python variable's type?
- Role of Bias in Neural Networks
- Keras Neural Nets, How to remove NaN values in output?
- Similar output for each input in training batch for neural network
- LSTM Nerual Network Input/Output dimensions error
- Having trouble getting TensorFlow to do something trivial
- Neural Network classification
- Getting neural network inputs back from outputs
- Extracting weights from best Neural Network in Tensorflow/Keras - multiple epochs
- How to resolve error when checking model input: expected convolution2d_input_9 to have 4 dimensions but got array with shape

ADS