Given one training data, namely 10 with a target of 0.0831. The data is used to train a multi-layer perceptron with the number of neurons in the hidden layer is one and added with refractive neurons, the activation function is a logistical function, o(a)=1/(1+e) with ez2,72. If all weights are initial 0.1 with n learning rate is 1, then after 2 epochs the weights in the output layer will be updated to