(a) Recall that for neural networks with sigmoid activation functions of the form (z) = 1 1+ exp(-z) the value of neuron k at layer / is computed as Wo + Wk,i v-1 iLayer-1 Design neural networks that compute the following Boolean functions, where x and x2 are Boolean inputs and we will treat the final output y as 1 if the output of the sigmoid unit is greater 0.5 and 0 otherwise. (i) Implement the logical OR function y = x V x with a single unit with three weights and two inputs. Explain whether you can implement the logical AND function with a single unit. (ii) Implement the XOR function with the smallest number of units and draw your network showing all the weights. (b) The senior management of ABC Bank consults you of using neural network to help their loan application approval process. Briefly explain to them how neural network can help and the process of implementation.