Faruk Ahmed
Griffith University
117 Papers
724 Citations
Faruk Ahmed is an academic researcher from Griffith University. The author has contributed to research in topics: Population & Vitamin. The author has an hindex of 34, co-authored 108 publications. Previous affiliations of Faruk Ahmed include University of Southampton & University of Queensland.
Chat about Author
Papers
•Posted Content
Improved Training of Wasserstein GANs
TL;DR: This work proposes an alternative to clipping weights: penalize the norm of gradient of the critic with respect to its input, which performs better than standard WGAN and enables stable training of a wide variety of GAN architectures with almost no hyperparameter tuning.
4.1K
•Posted Content
PixelVAE: A Latent Variable Model for Natural Images
Ishaan Gulrajani,Kundan Kumar,Faruk Ahmed,Adrien Ali Taïga,Francesco Visin,David Vazquez,Aaron Courville +6 more
TL;DR: PixelVAE as mentioned in this paper is a VAE model with an autoregressive decoder based on PixelCNN, which achieves state-of-the-art performance on binarized MNIST, competitive performance on 64x64 ImageNet, and high quality samples on the LSUN bedrooms dataset.
255
•Proceedings Article
PixelVAE: A Latent Variable Model for Natural Images
Ishaan Gulrajani,Kundan Kumar,Faruk Ahmed,Adrien Ali Taïga,Francesco Visin,David Vazquez,Aaron Courville +6 more
- 04 Nov 2016
TL;DR: PixelVAE as discussed by the authors is a VAE model with an autoregressive decoder based on PixelCNN, which achieves state-of-the-art performance on binarized MNIST, competitive performance on 64x64 ImageNet, and high quality samples on the LSUN bedrooms dataset.
Prevalence of Cardiovascular Disease and Associated Risk Factors among Adult Population in the Gulf Region: A Systematic Review
Najlaa M. Aljefree,Faruk Ahmed +1 more
- 27 Jan 2015
TL;DR: Effective preventative strategies and education programs are crucial in the Gulf region to reduce the risk of CVD mortality and morbidity in the coming years.
Removal of High-Density Salt-and-Pepper Noise in Images With an Iterative Adaptive Fuzzy Filter Using Alpha-Trimmed Mean
Faruk Ahmed,Swagatam Das +1 more
TL;DR: A novel adaptive iterative fuzzy filter for denoising images corrupted by impulse noise that operates in two stages-detection of noisy pixels with an adaptive fuzzy detector followed by denoised using a weighted mean filter on the “good” pixels in the filter window.
130