<p>This paper presents a neural network-based adaptive predefined-time control strategy for a class of high-order nonstrict-feedback nonlinear systems subject to unknown backlash-like hysteresis and external disturbances. An adaptive controller is designed by integrating the backstepping recursive methodology with the predefined-time stability framework. To approximate the unknown nonlinear dynamics, radial basis function neural networks (RBFNNs) are employed, while the power integrator technique is utilized to address the challenges posed by high-order system terms. A rigorous stability analysis is carried out using predefined-time Lyapunov theory, ensuring that all signals in the closed-loop system remain bounded and converge within a predefined time interval. The effectiveness and applicability of the proposed control approach are demonstrated through numerical simulations and a real-time case study involving a pendulum system.</p>