Using a mathematical model of a quadrotor, the Euler angle dynamics equations are analyzed to obtain a linear regression that describes the plant parametric uncertainty. Based on this representation, model reference adaptive control systems with both adjustable baseline controller and uncertainty compensator based on (i) a linear regression and (ii) a neural network are designed. Asymptotic stability of the augmented tracking error is proved for both systems. The results of numerical experiments demonstrate that the neural-network-based compensator, in contrast to the linear-regression-based one, copes with the matched uncertainty that is not included in the original description of the plant.