A neuro-sliding-mode control (NSMC) strategy was developed to handle the complex nonlinear dynamics and model uncertainties of flexible-link manipulators. A composite controller was designed based on a singularly perturbed model of flexible-link manipulators when the rigid motion and flexible motion...

A new approach for the design of two-dimensional (2-D) linear phase FIR digital filters based on a new neural networks algorithm (NNA) is provided. A compact expression for the transfer function of a 2-D linear phase FIR filter is derived based on its frequency response characteristic, and the NNA, ...

Topology design of artificial neural networks (ANNs) is an important problem for large scale applications. This paper describes a new efficient pruning method, the multi-weight optimal brain surgeon (MWOBS) method, to optimize neural network topologies. The advantages and disadvantages of the OBS an...

Newton's learning algorithm of NN is presented and realized. In theory, the convergence rate of learning algorithm of NN based on Newton's method must be faster than BP's and other learning algorithms, because the gradient method is linearly convergent while Newton's method has second order converge...

A neural-network-based adaptive gain scheduling back-stepping sliding mode control (NNAGS-BSMC) approach for a class of uncertain strict-feedback nonlinear system is proposed. First, the control problem of uncertain strict-feedback nonlinear systems is formulated. Second, the detailed design of NNAG...