The relative order and inverses of recurrent networks

Kambhampati, C.; Manchanda, Sahil; Delgado, Alberto; Green, Gary; Warwick, Kevin; Tham, M.T.

doi:10.1016/0005-1098(95)00098-4

Cited by 30 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main difficulty with recurrent neural networks is their training [13,16,17]. Various training strategies have been suggested in the literature, such as the backpropagation method [18], the conjugate gradient method [19], Levenberg-Marquardt optimization [20], or methods based on genetic algorithm (GAs) [21].…”

Section: Introductionmentioning

confidence: 99%

Nonlinear system identification for predictive control using continuous time recurrent neural networks and automatic differentiation

Al-Seyab

Cao

2008

Journal of Process Control

107

View full text Add to dashboard Cite

In this paper, a continuous time recurrent neural network (CTRNN) is developed to be used in nonlinear model predictive control (NMPC) context. The neural network represented in a general nonlinear statespace form is used to predict the future dynamic behavior of the nonlinear process in real time. An efficient training algorithm for the proposed network is developed using automatic differentiation (AD) techniques. By automatically generating Taylor coefficients, the algorithm not only solves the differentiation equations of the network but also produces the sensitivity for the training problem. The same approach is also used to solve the online optimization problem in the predictive controller. The proposed neural network and the nonlinear predictive controller were tested on an evaporation case study. A good model fitting for the nonlinear plant is obtained using the new method. A comparison with other approaches shows that the new algorithm can considerably reduce network training time and improve solution accuracy. The CTRNN trained is used as an internal model in a predictive controller and results in good performance under different operating conditions.

show abstract

Section: Introductionmentioning

confidence: 99%

Nonlinear system identification for predictive control using continuous time recurrent neural networks and automatic differentiation

Al-Seyab

Cao

2008

Journal of Process Control

107

View full text Add to dashboard Cite

show abstract

“…The main reason is due to the difficulty to solve the dynamic optimization problem associated with the continuous-time nonlinear model identification problem. So, the training of this type of neural network is difficult as reported by [PeB95,KaMC96,PBV03]. To solve the nonlinear optimization problem associated with CTRNN training, the calculation of a large number of dynamic sensitivity equations is required.…”

Section: Modelling With Artificial Neural Networkmentioning

confidence: 99%

“…The main difficulty with recurrent neural networks is in their training [PeB95,KaMC96,PBV03]. Various training strategies have been suggested in the literature, such as the backpropagation method [RuH86], the conjugate gradient method [LK99], Levenberg-Marquardt optimization [Mar63], or methods based on genetic algorithm (GAs) [Gol89].…”

Section: Nonlinear System Identification Using Ctrnnmentioning

confidence: 99%

Echtzeit-Implementierung von NMPC

Löw¹,

Obradović

2018

atp

View full text Add to dashboard Cite

Nonlinear Model Predictive Control (NMPC) is an aspiring control method for the implementation of advanced controller behavior. The present work shows the symbolic math implementation of a mechatronic system model containing aerodynamic nonlinearities modeled by Feedforward Neural Networks. Gradients for the optimization are obtained efficiently by exploiting the feedforward property of the Neural Networks and symbolic computation. Current research on the implementation of damage metrics into the cost function is stated briefly. In order to achieve real-time capability, the method Real-time Iteration is used.

show abstract

“…The main difficulty with recurrent neural networks is in their training[PeB95,KaMC96,PBV03]. Various training strategies have been suggested in the literature, such as the backpropagation method[RuH86], the conjugate gradient method [LK99], Levenberg-Marquardt optimization[Mar63], or methods based on genetic algorithm (GAs)[Gol89].…”

mentioning

confidence: 99%