问题
Assume you have a Neural Network, with no activation function, only known biases, weights, and an Output. Assuming it is possible, which I see no reason it wouldn't be, the first step you would do would be to subtract the biases from the Neural Network's Output, and after that, you would have to use some method to take the Outputs without the biases and with the weights to find the values of the Hidden Layer.
On paper, you could use substitution to find the values of the Hidden Layer, but I can't think of a way to easily implement this in code. Are there any simpler ways to do this?
回答1:
I have sucessfully been able to predict what Input would result in a certain Output given the structure and weights of a Neural Network by implementing an Algebraic Setup. I have all of the Neurons in the layer before the one we are calculating for as variables in an equation and I use a custom algorithm to solve for those variables.
来源：https://stackoverflow.com/questions/49887453/predicting-neural-network-input-from-its-output