Artificial neural network based model is estimated for modified shaped circular patch antenna. The Levenberg Marquardt (LM) algorithm is used to train the network, different antenna parameters in the X and Ku band are taken as input and delivers antenna dimensions as output. The dimensions obtained from estimated neural network model closely agrees the simulated results over the X and Ku band for FR4 epoxy substrate with 1.5 mm thickness. The simulation of microstrip patch antenna is carried out using Ansoft HFSS simulation software and the analysis of neural network model results are carried out using MATLAB. Thus, the estimated model can be used to obtain the antenna dimensions for circular patch antenna.