In Figure 1 below you see a very small neural network, which has one input unit, one hidden unit (logistic), and one output unit (linear). The nonlinear function in the logistic unit is defined by the formula o(x) = 1+exp(-2). Let's consider one training case. For that training case, the input value is 1 (as shown in the figure) and the target output value t is 1. We are using the standard squared loss function: E = = {(t y), where y is the output of the network. a) What is the output of the hidden unit and the output unit, for this training case? b) What is the loss, for this training case? c) What is the derivative of the loss with respect to w2, for this training case? Hint: Use chain rule d) What is the derivative of the loss with respect to wl, for this training case? Hint: the derivative of logistic function is defined as 0 (x) = 0(1) (1 0(x)) bias=0 Linear output unit W2= +4 bias= +2 Logistic hidden unit w1= -2 1 Input unit Figure 1: A small neural network with one hidden unit. The values for the weights and biases are given in the figure