Generative Adversarial Networks based on optimal transport: a survey

Kamsu-Foguem, Bernard; Shester, Gueuwou,; Kounta, Cheick Abdoul Kadir A.

doi:10.1007/s10462-022-10342-x

Cited by 5 publications

(3 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To improve the understanding of the development of WGANs and the relationships between different variants, a detailed analysis of the adversarial loss functions of the variants was carried out (Kamsu-Foguem & al., 2022). To clarify these developments, we have proposed a framework showing this temporal evolution with the intersections.…”

Section: Limitationsmentioning

confidence: 99%

See 1 more Smart Citation

Optimal Transport-based Loss Functions for Machine Learning

Kamsu Foguem,

Tiako,

Kounta

2024

Chronicle of Computing

View full text Add to dashboard Cite

This short paper briefly reports the essential facets of the article (Kamsu-Foguem & al., 2022) presented and discussed as a Journal First paper. The article overviews generative neural networks whose loss functions are based on optimal transport with the Wasserstein distance. This tool of mathematical origin allows interesting automatic learning to be obtained in a reasoning time under Lipschitz constraints. As the proposed studies are based on Wasserstein Generative Adversarial Networks (WGAN), we conclude this report with a short discussion on how WGAN currently supports critical, intelligent applications in our society and nearly all industry sectors.

show abstract

Section: Limitationsmentioning

confidence: 99%

“…

…”

mentioning

confidence: 99%

Optimal Transport-based Loss Functions for Machine Learning

Kamsu Foguem,

Tiako,

Kounta

2024

Chronicle of Computing

View full text Add to dashboard Cite

show abstract

“…On the other hand, GANs are an alternative class of AI algorithms used in unsupervised learning (UL) and consist of two parts. The first part (the generator) generates new data, and the second part (the discriminator) assesses the generated data, classifying it as real or fake data [35]. Great reconstruction results have also been obtained by an innovative sub-filter modeling method utilizing GANs for reactive turbulent flows [36].…”

Section: Generative Models Vaes-gansmentioning

confidence: 99%

From Sparse to Dense Representations in Open Channel Flow Images with Convolutional Neural Networks

Sofos,

Sofiadis,

Chatzoglou

et al. 2024

Inventions

View full text Add to dashboard Cite

Convolutional neural networks (CNN) have been widely adopted in fluid dynamics investigations over the past few years due to their ability to extract and process fluid flow field characteristics. Both in sparse-grid simulations and sensor-based experimental data, the establishment of a dense flow field that embeds all spatial and temporal flow information is an open question, especially in the case of turbulent flows. In this paper, a deep learning (DL) method based on computational CNN layers is presented, focusing on reconstructing turbulent open channel flow fields of various resolutions. Starting from couples of images with low/high resolution, we train our DL model to efficiently reconstruct the velocity field of consecutive low-resolution data, which comes from a sparse-grid Direct Numerical Simulation (DNS), and focus on obtaining the accuracy of a respective dense-grid DNS. The reconstruction is assessed on the peak signal-to-noise ratio (PSNR), which is found to be high even in cases where the ground truth input is scaled down to 25 times.

show abstract

Matrix Wasserstein distance generative adversarial network with gradient penalty for fast low-carbon economic dispatch of novel power systems

Yin,

Lin

2024

Energy

View full text Add to dashboard Cite

Generative Adversarial Networks based on optimal transport: a survey

Cited by 5 publications

References 70 publications

Optimal Transport-based Loss Functions for Machine Learning

Optimal Transport-based Loss Functions for Machine Learning

From Sparse to Dense Representations in Open Channel Flow Images with Convolutional Neural Networks

Matrix Wasserstein distance generative adversarial network with gradient penalty for fast low-carbon economic dispatch of novel power systems

Contact Info

Product

Resources

About