Artificial Neural networks (ANN’s) have now a days become efficient alternatives to conventional methods such as numerical modeling methods which could be computationally expensive, or analytical methods which could be difficult to obtain for new devices, or empirical models whose range and accuracy could be limited. ANN’s have also been used for solving a wide variety of RF and Microwave Computer Aided Design (CAD) problems. Analysis and design of a spiral inductor has been presented in this paper using ANN forward and inverse models. For the analysis a simple ANN forward model is used where the inputs are geometrical parameters and the outputs are electrical parameters and for the design, an Inverse model is used where the inputs are electrical parameters and the outputs are geometrical parameters. Direct Inverse model can be obtained by swapping the input and output data used to train the forward model. Training of neural network using inverse model may become difficult due to the non uniqueness of the input and output relationship in the model. A neural network inverse modeling approach is used to solve such a problem is by detecting multi valued solutions in the training data. The data containing multivalued solutions are divided into groups according to derivative information using a neural network forward model such that individual groups do not have the problem of multivalued solutions. Multiple inverse and forward models are built based on the divided data and are then combined to form a complete model. This Paper also presents a comparison of Direct inverse model and the indirect Inverse model.