3. Considera three-layer neural network with one output unit, 10 hidden units at each hidden layer, and a fivedimensional augmented feature vector as inputs. (a) Sketchthe network.(b) Write down the general expression on the derivative of the error function withrespect to a weight using back error propagation (i. e., gradient decent). (c) Verify the general expression by calculating the derivative of the error function with respect to a weight that connects the 5thhidden unit at the first hidden layer with the 6 hidden unit at the second hidden layer. (d) Write a pseudo algorithm that computes the increment of a weight that connects the 4thinput component with the 3rdhidden unit at the first hidden layer.