This study is laser focused on the use of artificial neural networks for the prediction of parameters of electric vehicles. The study is divided into five segments. The first segment involves the application of an artificial neural network in the prediction of parameters of pure electric vehicles for design simulation purposes. The second segment is based on the application of supervised machine learning for the prediction of fuel consumption in plug-in hybrid electric vehicles. The third segment involves the application of an inverse neural network approach for the prediction of multiple outputs for the design simulation of battery electric vehicles with the aid of supporting decision-making. The fourth segment is about the inverse function based on neural networks for predicting the parameters of the fuel economy label. The fifth part focuses on the application of inverse neural networks for predicting the parameters of a lithium-ion battery. In the first segment, artificial neural networks were applied to the prediction of parameters of pure electric vehicles. The objective of the study is to develop a model that can predict nine indispensable design parameters of pure electric vehicles. The developed model would assist in decision-making in terms of parameter selection. The categories of vehicles used include two-seater, full-size, compact, subcompact, mid-size, SUVs (standard), and station wagons (small). The accuracy of the model is promising for the predictions of the parameters. The second segment of the study employed supervised learning approaches to predict the fuel consumption of plug-in hybrid electric vehicles. The study also proposes adding additional parameters to the fuel economy label to make the information on it more comprehensible. The accuracy of the neural network was found to be higher than that of the multiple linear regression model. In the third segment of this study, an artificial neural network was employed to calculate and simulate the inverse functions of battery electric vehicle parameters. Nine variables were calculated and simulated as the outputs of the inverse function model at the same time. The procedure was completed for the nine cases where each of the augmented input variables of the inverse function model was the output of the direct function model. The accuracy was 142 times higher in terms of mean square error when electrical charge consumption and virtual functions were employed as input variables into the inverse function model. The proposed model will support faster decision-making in the design simulation of battery electric vehicles due to the large number of outputs simulated at once. The fourth aspect of the study focuses on the simulation of fuel consumption and fuel economy label parameters of plug-in hybrid electric vehicles using the inverse function approach of an artificial neural network. While fuel economy is a key factor in the design of plug-in hybrid electric vehicles, a fuel economy label can educate customers about the economic advantage of purchasing a particular car. The accuracy of the model was 29.1 times greater than that of the conventional inverse artificial neural network model. The fifth segment of the study introduces a feedforward deep inverse neural network for the prediction of parameters of the lithium-ion battery in electric vehicles. The accuracy of the proposed model was 44.43 times higher than in the traditional inverse deep neural network model.