The multilayer neural network in the figure below with one input, two output, and two hidden units are trained with gradient descent algorithm using parameters: learning rate 0.2 , and zero momentum. Assume the activation function for the neurons in the hidden layer is ReLU and in the out layer is linear.\ Assume initial weights and threshold as follow\ \\\\table[[W12,W13,W24,W25,W34,W35,O2,,,],[0.1,0.2,0.3,0.5,-1.2,1.1,0.1,-0.1,0.2,0.1]]\ If the training data is

x=0.5,Y4d=1,Y5d=0.2

. After one iteration of training, find\ The actual output of

Y5

\ The gradient error 83\ The correction weight of

\\\\Delta W13

\ Note:

Y4d

and

Y5d

are the desired output for neurons 4 and 5

The multilayer neural network in the figure below with one input, two output, and two hidden units are trained with gradient descent algorithm using parameters: learning rate 0.2 , and zero momentum. Assume the activation function for the neurons in the hidden layer is ReLU and in the out layer is linear. Assume initial weights and threshold as follow If the training data is X=0.5,Y4d=1,Y5d=0.2. After one iteration of training, find - The actual output of Y5 - The gradient error 83 - The correction weight of W13 Note: Y4d and Y5d are the desired output for neurons 4 and 5