1. Consider the following simple neural network with only one output node. Ignore the bias node for this example. The values on the edges indicate the weights associated with the "receiving no de Input Hidden Output 0.1 X1 0.35 Output 0.6 X2 = 0.90 Assume that the neurons have a Sigmoid activation function. You will need the following small snippet of Python code to compute sigmoid activation s for a value z. import numpy as np s = 1.0 / (1.0 + np.exp(-1.0 * z)) Or you can use a scientific calculator, MATLAB, etc. Refer to the class notes/slides and do the following Perform a forward pass on the network. . Perform a backward pass on the network. Let true input be y 0.5 . Update the weights at the output and hidden nodes using learning rate Choose the option which is correct below: O a) The error 6 at hidden node 1 will be +2.65037x10-3 O b) The error 8 at hidden node 2 will be -8.15581x10-3 O c) The error 8 at the output node is 0.0406 O d) The error 8 at the output node is-0.19 1. Consider the following simple neural network with only one output node. Ignore the bias node for this example. The values on the edges indicate the weights associated with the "receiving no de Input Hidden Output 0.1 X1 0.35 Output 0.6 X2 = 0.90 Assume that the neurons have a Sigmoid activation function. You will need the following small snippet of Python code to compute sigmoid activation s for a value z. import numpy as np s = 1.0 / (1.0 + np.exp(-1.0 * z)) Or you can use a scientific calculator, MATLAB, etc. Refer to the class notes/slides and do the following Perform a forward pass on the network. . Perform a backward pass on the network. Let true input be y 0.5 . Update the weights at the output and hidden nodes using learning rate Choose the option which is correct below: O a) The error 6 at hidden node 1 will be +2.65037x10-3 O b) The error 8 at hidden node 2 will be -8.15581x10-3 O c) The error 8 at the output node is 0.0406 O d) The error 8 at the output node is-0.19