def feedForward(self, training_example):
        #The values calculated during forward propagation are
        #stored to be used during backpropagation

        #Extract activations for first layer from training_example list
        self.a1 = np.array((training_example[0][0],training_example[0][1]))

        #Calculate the weighted inputs and activations for all other layers in the network
        self.z2 = np.dot(self.W1, self.a1.reshape(-1,1))
        self.a2 = self.sigmoid(self.z2)
        self.z3 = np.dot(self.W2, self.a2)
        self.a3 = self.sigmoid(self.z3)
        #return the activations of the neuron in the output layer
        return self.a3