Power-Type Varying-Parameter RNN for Solving TVQP Problems: Design, Analysis, and Applications

Zhang, Zhijun; Kong, Lingdong; Zheng, Lunan

doi:10.1109/tnnls.2018.2885042

Cited by 71 publications

(13 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, neural dynamic learning algorithm (NDLA) has been favored because of more rapid convergence and higher precision 37,42 , whose design formula is expressed aṡ…”

Section: Learning Algorithm Of Dynamic Learning Networkmentioning

confidence: 99%

“…e(t) ∈ R denotes deviation between prediction output and expectation over t.ė(t) denotes the derivative of the deviation e(t) with respect to t. λ > 0, λ ∈ R denotes NDLA parameter. Φ(•) denotes mapping function, which is a monotonically increasing and odd function 35,37,40,42 . Because NDLA is conducted in digital computer, such serial time expression is transformed into a discrete ones combined with Euler discrete formula 43 , which is shown as…”

Section: Learning Algorithm Of Dynamic Learning Networkmentioning

confidence: 99%

“…Furthermore, Zhang et al designed an adaptive multi-layer neural dynamics-based controllers of multi-rotor unmanned aerial vehicles for the sake of adapting to various complex transportation 36 . In addition, to solve time varying quadratic programming problem and robot tracking problem, a power-type varying-parameter recurrent neural network was proposed different from VP-CDNN 37,38 . To solve non-repetitive motion problem of redundant robot manipulators, Zhang et al proposed an adaptive fuzzy recurrent neural network, which can avoid the saturation of time varying design functions 39 .…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Bagging Dynamic Deep Learning Network for Diagnosing COVID-19

Zhang

Chen

Sun

2021

Preprint

Self Cite

View full text Add to dashboard Cite

COVID-19 is a serious epidemic all over the world. As an efficient way in intelligent medical services, using X-ray chest radiography image for automatically diagnosing COVID-19 provides huge assistances and conveniences for clinicians in practice. In this paper, a bagging dynamic deep learning network (B-DDLN) is proposed for diagnosing COVID-19 by intelligently recognizing X-ray chest radiography images. After a series of preprocessing steps for images, we pre-train convolution blocks as a feature extractor. For the extracted features, bagging dynamic learning network classifier is trained based on neural dynamic learning algorithm and bagging algorithm. B-DDLN connects feature extractor and bagging classifier in series. Experimental results verify that using the proposed B-DDLN can achieve 98.8889% testing accuracy, which illustrates the best diagnosis performances among existing methods on the open image set and provides evidences for further detection and treatment.

show abstract

“…In recent years, neural dynamic learning algorithm (NDLA) has been favored because of more rapid convergence and higher precision 37,42 , whose design formula is expressed aṡ…”

Section: Learning Algorithm Of Dynamic Learning Networkmentioning

confidence: 99%

Section: Learning Algorithm Of Dynamic Learning Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Bagging Dynamic Deep Learning Network for Diagnosing COVID-19

Zhang

Chen

Sun

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In other words, the NN is a kind of biological-heuristic computation and optimization network aiming at simulating nerve cells or neurons in human or biological nervous system, which is an important methods to realize artificial intelligence [24]. Owing to the superiorities such as the parallel processing as well as feasibility on hardware implementation, the approaches and models by exploiting ANNs [25]- [32], especially the RNNs, have been deemed as the systematic solvers for the time-dependent nonlinear optimization [33]- [36]. Especially, the neural network models via the negative gradient direction strategy by constructing the scalar valued energy functions have been introduced and investigated for some online scientific problems handling [3], [37], [38].…”

Section: Introductionmentioning

confidence: 99%

Active Sensing of Robot Arms Based on Zeroing Neural Networks: A Biological-Heuristic Optimization Model

Gong

Chen

2020

IEEE Access

View full text Add to dashboard Cite

Conventional biological-heuristic solutions via zeroing neural network (ZNN) models have achieved preliminary efficiency on time-dependent nonlinear optimization problems handling. However, the investigation on finding a feasible ZNN model to solve the time-dependent nonlinear optimization problems with both inequality and equality constraints still remains stagnant because of the nonlinearity and complexity. To make new progresses on the ZNN for time-dependent nonlinear optimization problems solving, this paper proposes a biological-heuristic optimization model, i.e., inequality and equality constrained optimization ZNN (IECO-ZNN). Such a proposed IECO-ZNN breaks the conditionality that the solutions via ZNN for solving nonlinear optimization problems can not consider the inequality and equality constraints at the same time. The time-dependent nonlinear optimization problem subject to inequality and equality constraints is skillfully converted to a time-dependent equality system by exploiting the Lagrange multiplier rule. The design process for the IECO-ZNN model is presented together with its new architecture illustrated in details. In addition, the conversion equivalence, global stability as well as exponential convergence property are theoretically proven. Moreover, numerical studies, real-world applications to robot arm active sensing, and comparisons sufficiently verify the effectiveness and superiority of the proposed IECO-ZNN model for the time-dependent nonlinear optimization with inequality and equality constraints. INDEX TERMS Zeroing neural networks (ZNNs), biological-heuristic optimization, nonlinear optimization, inequality and equality constraints, robot motion control. * (t) = {(t, x * (t))|∂f (x * (t), t)/∂x * (t) = 0},

show abstract

“…The Recurrent Neural Networks (RNNs) are popularly known for the time-series data since they can understand the contextual information stored in sequential data. RNNs are popularly used in several real-world applications [18][19][20][21][22][23][24][25]. Likewise, they have used in the control of the wall the following robot as well.…”

mentioning

confidence: 99%

An Optimally Configured HP-GRU Model Using Hyperband for the Control of Wall Following Robot

Khan

Salik

et al. 2021

IJRCS

View full text Add to dashboard Cite

In this paper, we presented an autonomous control framework for the wall following robot using an optimally configured Gated Recurrent Unit (GRU) model with the hyperband algorithm. GRU is popularly known for the time-series or sequence data, and it overcomes the vanishing gradient problem of RNN. GRU also consumes less memory and is computationally more efficient than LSTMs. The selection of hyper-parameters of the GRU model is a complex optimization problem with local minima. Usually, hyper-parameters are selected through hit and trial, which does not guarantee an optimal solution. To come around this problem, we used a hyperband algorithm for the selection of optimal parameters. It is an iterative method, which searches for the optimal configuration by discarding the least performing configurations on each iteration. The proposed HP-GRU model is used on a dataset of SCITOS G5 robots with 24 sensors mounted. The results show that HP-GRU has a mean accuracy of 0.9857 and a mean loss of 0.0810, and it is comparable with other deep learning algorithms.

show abstract

Power-Type Varying-Parameter RNN for Solving TVQP Problems: Design, Analysis, and Applications

Cited by 71 publications

References 55 publications

A Bagging Dynamic Deep Learning Network for Diagnosing COVID-19

A Bagging Dynamic Deep Learning Network for Diagnosing COVID-19

Active Sensing of Robot Arms Based on Zeroing Neural Networks: A Biological-Heuristic Optimization Model

An Optimally Configured HP-GRU Model Using Hyperband for the Control of Wall Following Robot

Contact Info

Product

Resources

About