A Neural Net Approach to Real-Time Adaptive Array

A novel Hopfield-type neural net with a number of graded-response neurons is proposed for implementing the real-time adaptive antenna array, which are steered by updating the weights across the array in order to maximize the output signal-to-noise ratio. A fourth order Runge-Kutta simulation is conducted to verify the performance of the proposed analog circuit. It shows that the circuit operates at a much higher speed than conventional techniques and the computation time of solving a linear array of ten elements is about 0.1ns for RC = 5 × 10¿12.