Solve the following three-bit parity problem with a 3-3-1 network with bias by applying neural network learning. That is, the input layer has three nodes, the hidden layer has three nodes and the output layer has one node. a) Analyze the function of the hidden layer, just like what we did about the XOR problem in class. b) Retrain several times from a new random point until you get a local (but not global) minimum. Analyze the function of the hidden units now. c) How many examples are properly classified for your local minimum