The problem of chaotic time series prediction is studied in various disciplines now including engineering, medical and econometric applications. Chaotic time series are the output of a deterministic system with positive Liapunov exponent. A time series prediction is a suitable application for a neuronal network predictor. The NN approach to time series prediction is non-parametric, in the sense...

This paper introduces a class of nonlinear discrete-time dynamic models that generalize familiar linear model structures; our motivation is to explore the extent to which known results for the linear case do or do not extend to this nonlinear class. The results presented here are based on a complete characterization of the solution of the associative functional equation F[F(x, y),z] — F[x, F(y,...

This paper focuses on a critical component of the situational awareness (SA), the neural control of autonomous constant depth flight of an autonomous underwater vehicle (AUV). Autonomous constant depth flight is a challenging but important task for AUVs to achieve high level of autonomy under adverse conditions. The fundamental requirement for constant depth flight is the knowledge of the depth...

This paper investigates optimal structure of Piplined Recurrent Neural Network (PRNN) for adaptive traffic prediction of MPEG video signal via dynamic ATM networks. The traffic signal of each picture type (I, P, and B) of MPEG video is characterized by a nonlinear autoregressive moving average (NARMA) process. Since those modules of PRNN can be performed simultaneously in a pipelined parallelis...

One of the most difficult problems in using dynamic reservoirs like echo state networks for signal processing is the choice of reservoir network parameters like connectivity or spectral radius of the weight matrix. In this article, we investigate the properties of an unsupervised intrinsic plasticity rule for signal specific adaptive shaping of the reservoir, which is local in space and time an...

In this paper, output feedback adaptive control is investigated for a class of nonlinear systems in output-feedback form with unknown control gains. To construct output feedback control, the system is transformed into the form of the NARMA (nonlinear-auto-regressive-moving-average) model, based on which future output prediction is carried out. With employment of the predicted future output, a c...

The NARMA model is an exact representation of the input-output behavior of finitedimensional nonlinear discrete-time dynamical systems in the neighborhood of the equilibrium state. However, it is inconvenient for purposes of adaptive control due to its nonlinear dependence on the control input, even by using the neural network method. In this paper, we introduce a so called model-free adaptive ...

Abstract—This paper focuses on a critical component of the situational awareness (SA), the control of autonomous vertical flight for vectored thrust aerial vehicle (VTAV). With the SA strategy, we proposed a neural network motion control procedure to address the dynamics variation and performance requirement difference of flight trajectory for a VTAV. This control strategy with using of NARMAL2...