Abstracf-Thi,y puper proposes (1 new non-lineor adoptive PID hosed multiple controller incorporating a neural network learning sub-model. The unknown non-linear plant is represenred b.v an equivalent model consisring of a linear time-vaving sub-model plus a non-linear neuralnetworks based learning sub-model. The proposed multiple controller merhodologv provides the designer with a choice of using either o conwntionol PID Ser/tuning controller. a PID based pole-placement conrroller, or 4 nek.1.v proposed PID based polezero placement controller through the Pick U switch. Simulation resulrs using il non-linear plant model demonstrare rhe effectiveness of the proposed multiple controller. wirh respect to crocking set-point changes w,ith rhe desired speed of response, penalising excessive control action, and ils application to non-minimum phase and unstable s.vs1em.T.