(b) In neural networks, the sigmoid function determines the activation values of the units in the hidden layer. For an MLP implementing non-linear regression the update rules are the following: Avh=1 En E(r y)zh Awnj = n (" y)vnn(1 En); where x'; is input at unit j and th is the activation function of hidden unit h. Derive the update rules for an MLP implementing the same non-liaear regression with two hidden layers, where the second layer uses the index l. Use when to denote weights between the 1st and the 2nd hidden layers and winj to denote weights between the input layer and the 1st hidden layer. (Recall the backpropogation rule og ) (b) In neural networks, the sigmoid function determines the activation values of the units in the hidden layer. For an MLP implementing non-linear regression the update rules are the following: Avh=1 En E(r y)zh Awnj = n (" y)vnn(1 En); where x'; is input at unit j and th is the activation function of hidden unit h. Derive the update rules for an MLP implementing the same non-liaear regression with two hidden layers, where the second layer uses the index l. Use when to denote weights between the 1st and the 2nd hidden layers and winj to denote weights between the input layer and the 1st hidden layer. (Recall the backpropogation rule og )