This paper focuses on designing a discrete-time lateral-directional co
ntrol law for a high-performance aircraft using neural networks. The c
ontrol law structure is composed of feedback and filter components for
mulated in the form of a three layer feedforward neural network whose
parameters are adjusted by a gradient descent algorithm to provide sta
bilization about the aircraft center of mass and asymptotic tracking o
f pilot command input. The number of parameters was chosen in an ad ho
c manner. Only rate gyro and lateral accelerometer outputs are availab
le for feedback, whereas rudder pedal and lateral stick commands are i
nput signals to the filter. Linear simulation results at an operating
point within the aircraft's envelope in the presence of atmospheric tu
rbulence and actuator and sensor noises shed light on the ability of n
eural networks to serve as a practical tool for flight control law des
igners.