Uncertain design optimization of automobile structures: A survey

Xu, Xipeng; Huang, Cheng; Li, Chongchong; Zhao, Gang; Li, Xiaojie; Ma, Chao

doi:10.3934/era.2023062

Cited by 3 publications

(1 citation statement)

References 154 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The literature examines Graph Neural Networks (GNNs) in-depth, covering general knowledge, network structures, potential gaps, and perspectives through various surveys [1,2,12,15,18,19,[36][37][38][39][40][41][42][43][44][45][46][47]. In addition, the existing literature includes surveys and reviews focusing on specific applications [48][49][50][51].…”

Section: Introductionmentioning

confidence: 99%

A Survey of Computationally Efficient Graph Neural Networks for Reconfigurable Systems

Kose,

Nunez-Yanez,

Piechocki

et al. 2024

Preprint

View full text Add to dashboard Cite

Graph Neural Networks (GNNs) are powerful models capable of managing intricate connections in non-Euclidean data, such as social networks, physical systems, chemical structures, and communication networks. Despite their effectiveness, the large-scale and complex nature of graph data demands substantial computational resources and high performance during both training and inference stages, presenting significant challenges, particularly in the context of embedded systems. Recent studies on GNNs have investigated both software and hardware solutions to enhance computational efficiency. Earlier studies on Deep Neural Networks (DNNs) have indicated that methods like reconfigurable hardware and quantization are beneficial in addressing these issues. Unlike DNN research, studies on efficient computational methods for GNNs are less developed and require more exploration. This survey reviews the latest developments in quantization and FPGA-based acceleration for GNNs, showcasing the capabilities of reconfigurable systems (often FPGAs) to offer customized solutions in environments marked by significant sparsity and the necessity for dynamic load management. It also emphasizes the role of quantization in reducing both computational and memory demands through the use of fixed-point arithmetic and streamlined vector formats. This paper concentrates on low-power, resource-limited devices over general hardware accelerators and reviews research applicable to embedded systems. Additionally, it provides a detailed discussion of potential research gaps, foundational knowledge, obstacles, and prospective future directions.

show abstract

Section: Introductionmentioning

confidence: 99%

A Survey of Computationally Efficient Graph Neural Networks for Reconfigurable Systems

Kose,

Nunez-Yanez,

Piechocki

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

Regularization scheme for uncertain fuzzy differential equations: Analysis of solutions

Martynyuk,

Stamov,

Stamova

et al. 2023

era

View full text Add to dashboard Cite

<abstract><p>In this paper a regularization scheme for a family of uncertain fuzzy systems of differential equations with respect to the uncertain parameters is introduced. Important fundamental properties of the solutions are discussed on the basis of the established technique and new results are proposed. More precisely, existence and uniqueness criteria of solutions of the regularized equations are established. In addition, an estimation is proposed for the distance between two solutions. Our results contribute to the progress in the area of the theory of fuzzy systems of differential equations and extend the existing results to the uncertain case. The proposed results also open the horizon for generalizations including equations with delays and some modifications of the Lyapunov theory. In addition, the opportunities for applications of such results to the design of efficient fuzzy controllers are numerous.</p></abstract>

show abstract

On the regularization and matrix Lyapunov functions for fuzzy differential systems with uncertain parameters

Martynyuk,

Stamov,

Stamova

et al. 2023

era

View full text Add to dashboard Cite

<abstract><p>In this paper, for a regularized fuzzy system, a generalization of the direct Lyapunov method is adapted on the base of matrix-valued Lyapunov-like functions. First, the new concept of a regularization scheme for fuzzy systems is discussed and the matrix-valued Lyapunov function technique is introduced. Then, sufficient conditions are established for the boundedness and stability of the equilibrium set of solutions of the regularized fuzzy system of differential equations. Scalar and vector Lyapunov-type functions are used based on an auxiliary matrix-valued function. Finally, a discussion is offered for the future directions of the proposed approach. Since the strategies for the analysis of the stability of fuzzy models are very important in numerous aspects, we expect that our results will inspire researchers to develop the introduced concept.</p></abstract>

show abstract

Uncertain design optimization of automobile structures: A survey

Cited by 3 publications

References 154 publications

A Survey of Computationally Efficient Graph Neural Networks for Reconfigurable Systems

A Survey of Computationally Efficient Graph Neural Networks for Reconfigurable Systems

Regularization scheme for uncertain fuzzy differential equations: Analysis of solutions

On the regularization and matrix Lyapunov functions for fuzzy differential systems with uncertain parameters

Contact Info

Product

Resources

About