Create a 2 input and 1 output multilayer neural network, which could behave as a non-linear classifier to separate the following linearly un-separable training data. Training data has two attributes and one label. Each attribute could be 1 or 0 and the label is 1 (positive) or 0 (negative). Each node used in multilayer neural network may just perform perceptron function. List perceptron function (activation function) used.

X1 X2 0 1 0 1 Output X1 X2 0 1 0 1 Output