Recurrent neural networks have become popular models for system identiication and time series prediction. NARX (Nonlinear AutoRegressive models with eXogenous inputs) neural network models are a popular subclass of recurrent networks and have been used in many applications. Though embedded memory can be found in all recurrent network models, it is particularly prominent in NARX models. We show ...

Chaotic time-series is a dynamic nonlinear system whose features can not be fully reflected by Linear Regression Model or Static Neural Network. While Nonlinear Autoregressive with eXogenous input includes feedback of network output, therefore, it can better reflect the system’s dynamic feature. Take annual active times of sunspot as an example, after verifying the chaos of sunspot time-series ...

A neural network based-approach for structural health monitoring was presented. The proposed approach involves two steps. The first step, system identification, uses NARX (Non-linear Auto-Regressive with eXogenous) neural networks to identify the undamaged and damaged states of a structural system. The second step, structural damage detection, uses the aforementioned trained NARX neural network...

Recurrent neural networks have become popular models for system identification and time series prediction. Nonlinear autoregressive models with exogenous inputs (NARX) neural network models are a popular subclass of recurrent networks and have been used in many applications. Although embedded memory can be found in all recurrent network models, it is particularly prominent in NARX models. We sh...

It has previously been shown that gradient-descent learning algorithms for recurrent neural networks can perform poorly on tasks that involve long-term dependencies, i.e. those problems for which the desired output depends on inputs presented at times far in the past. We show that the long-term dependencies problem is lessened for a class of architectures called nonlinear autoregressive models ...

It has recently been shown that gradient-descent learning algorithms for recurrent neural networks can perform poorly on tasks that involve long-term dependencies, i.e., those problems for which the desired output depends on inputs presented at times far in the past. We show that the long-term dependencies problem is lessened for a class of architectures called Nonlinear AutoRegressive models w...