The features of the synthesis of neural controllers for the car speed control system are considered in the article. The task of synthesis is to determine the weight coefficients of neural networks that provide the implementation of proportional and proportional-integral-derivative control laws. The synthesis of controllers is based on an approach that uses a reversed model of the standard. A model of the car speed control system with the use of permitting subsystems has been developed, with the help of which one of the synthesized controllers is connected under certain specified conditions. Using the iterative programming and mathematical modeling environment in MATLAB and using the Simulink package, a structural scheme for controlling the speed of the car was constructed and simulated using synthesized neural controllers.