New discrete-time zeroing neural network for solving time-variant underdetermined nonlinear systems under bound constraint

Huang, Shaobin; Ma, Zhisheng; Song, Yu; Han, Yuxing

doi:10.1016/j.neucom.2021.11.004

Cited by 5 publications

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Require: x (0) , g, ε 1: {x (0) is the initial box, g(•) is the interval extension of the function g : R n → R m } 2: {L ver -verified solution boxes, L pos -possible solution boxes} 3: L ver = ∅ 4: L pos = ∅ 5: x = x (0) 6: loop 7: compute y = g(x) bisect (x), obtaining x (1) and x (2) 23:…”

Section: A Interval Methods and Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Developing an interval method for training denoising autoencoders by bounding the noise

Kubica

2023

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

This paper discusses prospects of using interval methods to training denoising autoencoders. Advantages and disadvantages of using the interval approach are discussed. It is proposed to formulate the problem of training the proper neural network as a constraint-satisfaction, and not optimization, problem. Pros and cons of this approach are considered. Preliminary numerical experiments are also presented.

show abstract

Section: A Interval Methods and Neural Networkmentioning

confidence: 99%

“…Interval methods, while used by several authors for neural network training (see, e.g., [1], [2], [3], [4], [5], [6], [7]), have rarely been used in conjunction with AE, so far. The only known exception is the paper [8].…”

Section: Introductionmentioning

confidence: 99%

Developing an interval method for training denoising autoencoders by bounding the noise

Kubica

2023

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

show abstract

New discrete-time zeroing neural network for solving time-dependent linear equation with boundary constraint

Cang,

Qiu,

Xue

et al. 2024

Artif Intell Rev

View full text Add to dashboard Cite

Recently, continuous- and discrete-time models of a zeroing neural network (ZNN) have been developed to provide online solutions for the time-dependent linear equation (TDLE) with boundary constraint. This paper presents a novel approach to address the bound-constrained TDLE (BCTDLE) problem by proposing a new discrete-time ZNN (DTZNN) model. The proposed DTZNN model is designed using the Taylor difference formula to discretize the previous continuous-time ZNNN (CTZNN) model. Theoretical analysis indicates the computational property of the proposed DTZNN model, and numerical results further demonstrate its validity. The applicability of the proposed DTZNN model is finally confirmed via its application to the motion planning of a PUMA560 robotic arm.

show abstract

From Gauss–Newton method solving nonlinear least squares problem of static overdetermined system to multi-instant neurodynamic algorithms handling future time-variant situation

Wu,

Zhang

2024

Nonlinear Dyn

View full text Add to dashboard Cite

New discrete-time zeroing neural network for solving time-variant underdetermined nonlinear systems under bound constraint

Cited by 5 publications

References 27 publications

Developing an interval method for training denoising autoencoders by bounding the noise

Developing an interval method for training denoising autoencoders by bounding the noise

New discrete-time zeroing neural network for solving time-dependent linear equation with boundary constraint

From Gauss–Newton method solving nonlinear least squares problem of static overdetermined system to multi-instant neurodynamic algorithms handling future time-variant situation

Contact Info

Product

Resources

About