Results 41 to 50 of about 339,375 (294)
DC-DC Converter Design Issues for High-Efficient DC Microgrid
Communications, 2019 In this article, the electrical properties, as well as the economic aspects of the modular and non-modular solution of the DC-DC photovoltaic converter for DC microgrid subsystem, are described.
Michal Frivaldsky, Jan Morgos
doaj +1 more source
CoRR, 2017 We introduce a new algorithm named WGAN, an alternative to traditional GAN training. In this new model, we show that we can improve the stability of learning, get rid of problems like mode collapse, and provide meaningful learning curves useful for debugging and hyperparameter searches.
Martín Arjovsky +2 more
openaire +2 more sources
CoRR, 2017 In this paper, we analyze the numerics of common algorithms for training Generative Adversarial Networks (GANs). Using the formalism of smooth two-player games we analyze the associated gradient vector field of GAN training objectives. Our findings suggest that the convergence of current algorithms suffers due to two factors: i) presence of eigenvalues
Mescheder, L., Nowozin, S., Geiger, A.
openaire +5 more sources
CoRR, 2018 A longstanding problem in machine learning is to find unsupervised methods that can learn the statistical structure of high dimensional signals. In recent years, GANs have gained much attention as a possible solution to the problem, and in particular have shown the ability to generate remarkably realistic high resolution sampled images.
Eitan Richardson, Yair Weiss
openaire +4 more sources
Remote Sensing, 2020 The existence of clouds is one of the main factors that contributes to missing information in optical remote sensing images, restricting their further applications for Earth observation, so how to reconstruct the missing information caused by clouds is ...
Jianhao Gao +4 more
doaj +1 more source
Active Damping in Series Connected Power Modules with Continuous Output Voltage
Power Electronics and Drives, 2021 This paper presents a modular and scalable power electronics concept for motor control with continuous output voltage. In contrast to multilevel concepts, modules with continuous output voltage are connected in series.
Ulmer Sabrina +2 more
doaj +1 more source
The GAN is dead; long live the GAN! A Modern GAN Baseline
Advances in Neural Information Processing Systems 37There is a widely-spread claim that GANs are difficult to train, and GAN architectures in the literature are littered with empirical tricks. We provide evidence against this claim and build a modern GAN baseline in a more principled manner. First, we derive a well-behaved regularized relativistic GAN loss that addresses issues of mode dropping and non ...
Nick Huang +3 more
openaire +4 more sources
Prb-GAN: A Probabilistic Framework for GAN Modelling
CoRR, 2021 Generative adversarial networks (GANs) are very popular to generate realistic images, but they often suffer from the training instability issues and the phenomenon of mode loss. In order to attain greater diversity in GAN synthesized data, it is critical to solving the problem of mode loss.
Blessen George +2 more
openaire +2 more sources
Snehalikalall/LSH-GAN: LSH-GAN
, 2022 LSH-GAN enables in-silico generation of cells for small sample high dimensional scRNA-seq ...
Snehalikalall
core +1 more source