A Delay Damage Model Selection Algorithm For NARX Neural Networks - Signal Processing, IEEE Transactions on
نویسندگان
چکیده
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 show that using intelligent memory order selection through pruning and good initial heuristics significantly improves the generalization and predictive performance of these nonlinear systems on problems as diverse as grammatical inference and time series prediction.
منابع مشابه
A delay damage model selection algorithm for NARX neural networks
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 ...
متن کاملDamage detection and structural health monitoring of ST-37 plate using smart materials and signal processing by artificial neural networks
Structural health monitoring (SHM) systems operate online and test different materials using ultrasonic guided waves and piezoelectric smart materials. These systems are permanently installed on the structures and display information on the monitor screen. The user informs the engineers of the existing damage after observing signal loss which appears after damage is caused. In this paper health...
متن کاملLearning long-term dependencies in NARX recurrent neural networks
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 ...
متن کاملA cross-associative neural network for SVD of non-squared data matrix in signal processing
This paper proposes a cross-associative neural network (CANN) for singular value decomposition (SVD) of a non-squared data matrix in signal processing, in order to improve the convergence speed and avoid the potential instability of the deterministic networks associated with the cross-correlation neural-network models. We study the global asymptotic stability of the network for tracking all the...
متن کاملLearning Long-Term Dependencies in NARX Recurrent Neural Networks - Neural Networks, IEEE Transactions on
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...
متن کامل