How to calculate feed-forward (forward-propagation) in neural network?

Question

In the figure below, a neural network is shown. Calculate the following:

1) How many neurons do we have in the input layer and the output layer?

2) How many hidden layers do we have?

3) If all the weights initialized with 1 ($w1=w2=w3=...=w19=1$), what is the output of this network after feed-forward for the sample shown in the figure (X = (x1,x2,x3) = (2,5,3) and y=10)? What is the error of the network ($\text { Error }=\frac{1}{2}(\hat{y}-y)^{2}$)? Assume activation functions for all neurons except the output neuron is $f(z)=z$. 

4) If we change the activation function of all the neurons in the second hidden layer to Sigmoid ($S(x)=\frac{1}{1+e^{-x}}=\frac{e^{x}}{e^{x}+1}$), what would be the output of the network after this change? Calculate the error as well.

Answer 1

Please take a look at the solution below. The second answer is close to the correct answer

Comments

There is an error in the last part of the question.

yhat should be equal to 0.993.

The negative sign was left out of the calculation.

---

agreed with hamzasi, I got the same answer, y hat = 0.993, Error = 40.56