Please explain as best you can how to get the answer(with theory) and I will give you a thumbs up. Don't simply use chat GPT.

(a) Draw the decision boundary, boundaries, or none (no boundary) created by the following neural networks trained on the two-class data ( and ) shown in Fig. Q3. (i) A neural network with 2 inputs, one hidden layer, and one sigmoid output, where the hidden layer has 2 hidden nodes with hyperbolic tangent activation functions. (5 marks) (ii) A neural network with 2 inputs, one hidden layer, and two softmax outputs, where the hidden layer has 2 hidden nodes with hyperbolic tangent activation functions. (5 marks) (iii) A neural network with 2 inputs, two hidden layers, and one sigmoid output, where each hidden layer has 2 hidden nodes with hyperbolic tangent activation functions. (5 marks) (iv) A neural network with 2 inputs, two hidden layers, and two softmax outputs, where each hidden layer has 2 hidden nodes with linear activation functions