3. Apply the back-propagation algorithm to find the weights corrections of a neural network after applying the input-output pattern ({0.9,0.4,0.2},2.5). Assume that the network has a single hidden layer with 3 neurons. All weights are initially set to 0.3 and all thresholds are 0.5. All neurons use the sigmoid activation function with a learning rate of 0.2. You are required to