Further Result on Input-to-State Stabilization of Dynamic Neural Network Systems

This paper presents an approach for input-to- state stabilization of dynamic neural networks, which extends the existing result in the literature to a wider class of systems. With the help of Sontag´s formula, we create a scalar function to develop a new methodology for input-to-state stabilization of a class of dynamic neural network systems without a restriction on the number of inputs. In addition, the proposed design achieves global asymptotic stability and global inverse optimality with respect to a meaningful cost functional. A numerical example demonstrates the performance of the approach.