Thefollowingimageillustratesthetopologyofafeedforwardneuralnetworkthathas two sensing neurons (Neurons 1 and 2), two hidden processing neuron (Neurons 3, and 4), and two processing output neurons (Neurons 5 and 6). w3,0 =0.1 1 w3,1 =0.1 3 w5,3 =0.1 w6,3 =0.1 w4,1 =0.2 w5,0 =0.1 5 w4,0 =0.1 w6,0 =0.1 w3,2 =0.2 w5,4 =0.2 2 w4,2=0.3 4 w6,4=0.2 6 (a) Assuming that the processing neurons use logistic activation functions, that the input to the network is Neuron 1 = 0.3 and Neuron 2 = 0.6, and that the desired output for this input is Neuron 5 = 0.7 and Neuron 6 = 0.4: i. Calculatetheoutputgeneratedbythenetworkinresponsetothisinput. ii. Calculatethesumofsquarederrorsforthisnetworkforthisexample. iii. Calculate the values for each of the processing neurons in the network (i.e., 6, 5, 4, 3). iv. Using the values you calculated above, calculate the sensitivity of the error of the network to changes in each of the weights of the network (i.e., BE{Bw , 6,4 BE{Bw6,3, BE{Bw6,0, BE{Bw5,4, BE{Bw5,3, BE{Bw5,0, BE{Bw4,2, BE{Bw4,1, BE{Bw4,0, BE{Bw3,2, BE{Bw3,1, BE{Bw3,0). v. Assuming a learning rate of " 0.1, calculate the updated values for each of the weights in the network (w6,4,w6,3,w6,0,w5,4, w5,3, w5,0, w4,2,w4,1,w4,0, w3,2, w3,1, w3,0,) after the processing of this single training example. vi. Calculate