This paper proposes incremental deep learning methods for training neural networks to control the response of complex nonlinear dynamic systems. By analyzing the complexity of the task to be fulfilled by the neural network, learning strategies are formulated and implemented in an incremental scheme starting from simple tasks and continuing with increasingly complex tasks. The Dynamic Back Propagation algorithm is used for training the neuro-controller in each step of the incremental learning process, considering the system nonlinear dynamics. The results obtained in the control of highly unstable nonlinear systems, and the positioning control of mobile robots verify the effectiveness of the proposed incremental deep learning strategies.