2022
DOI: 10.3389/fnbot.2022.1065256
|View full text |Cite
|
Sign up to set email alerts
|

A robust zeroing neural network and its applications to dynamic complex matrix equation solving and robotic manipulator trajectory tracking

Abstract: Dynamic complex matrix equation (DCME) is frequently encountered in the fields of mathematics and industry, and numerous recurrent neural network (RNN) models have been reported to effectively find the solution of DCME in no noise environment. However, noises are unavoidable in reality, and dynamic systems must be affected by noises. Thus, the invention of anti-noise neural network models becomes increasingly important to address this issue. By introducing a new activation function (NAF), a robust zeroing neur… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
6
0

Year Published

2023
2023
2025
2025

Publication Types

Select...
9

Relationship

2
7

Authors

Journals

citations
Cited by 16 publications
(6 citation statements)
references
References 39 publications
0
6
0
Order By: Relevance
“…To enhance the training stability, we incorporate residual connections. The optimizer employed is NAdam (Dozat, 2016 ; Li et al, 2022 ), with an initial learning rate of 0.01, modulated using a cosine annealing learning rate scheduler (Jin et al, 2022 ). We train the models over 1,000 and 2,000 epochs, respectively.…”
Section: Resultsmentioning
confidence: 99%
See 1 more Smart Citation
“…To enhance the training stability, we incorporate residual connections. The optimizer employed is NAdam (Dozat, 2016 ; Li et al, 2022 ), with an initial learning rate of 0.01, modulated using a cosine annealing learning rate scheduler (Jin et al, 2022 ). We train the models over 1,000 and 2,000 epochs, respectively.…”
Section: Resultsmentioning
confidence: 99%
“…In simulations of opinion dynamics, each block of NODEs consists of three fully connected layers, each followed by an exponential linear unit (ELU) activation function, as shown in The optimizer employed is NAdam (Dozat, 2016;Li et al, 2022), with an initial learning rate of 0.01, modulated using a cosine annealing learning rate scheduler (Jin et al, 2022). We train the models over 1,000 and 2,000 epochs, respectively.…”
Section: Settings For Opinion Dynamicsmentioning
confidence: 99%
“…Moreover, the problems of dynamic coupling, dynamic limitations caused by the environments, and delay problems of the controller are also should be considered, and they complicate the control process of manipulator trajectory tracking. Therefore, researchers have proposed the PID control [9,10], feedback control [11], finitetime control [12][13][14], fuzzy control [15][16][17][18] and neural network control [19][20][21][22][23][24][25] to solve the above problems.…”
Section: Introductionmentioning
confidence: 99%
“…Several research studies (Graves et al, 2005;Rueckert et al, 2017;Liu et al, 2019) have consistently reported better performance of Recurrent Neural Networks (RNNs), specifically bidirectional RNNs (BRNNs), over non-recurrent ANNs in timeseries problems (of a moderate number of inputs), such as the one we are dealing with. RNNs are extensively used to model different dynamic systems (Jin et al, 2022). Particularly, in robotics, unidirectional RNNs have been trained to learn the inverse or direct dynamics of rigid robots (Mukhopadhyay et al, 2019;Wang et al, 2020).…”
Section: Introductionmentioning
confidence: 99%