Fig. Q3-1 shows a neural network involving a single hidden neuron and an output neuron both adopting hard-limiter as the activation function. Construct (1) the decision regions, and (2) truth table for the network. What type of logic gate is the network be able to imitate? (b) What are the advantages of using the radial basis function (RBF) model over the multi-layer perceptron (MLP) model? (c) What is a training set and how is it used to train neural networks