Zobrazeno 1 - 10
of 195
pro vyhledávání: '"Fady Alajaji"'
Publikováno v:
Entropy, Vol 26, Iss 4, p 290 (2024)
A unifying α-parametrized generator loss function is introduced for a dual-objective generative adversarial network (GAN) that uses a canonical (or classical) discriminator loss function such as the one in the original GAN (VanillaGAN) system. The g
Externí odkaz:
https://doaj.org/article/43f8583df6cd4f14b210c794705f512a
Publikováno v:
Entropy, Vol 25, Iss 4, p 668 (2023)
The error probability of block codes sent under a non-uniform input distribution over the memoryless binary symmetric channel (BSC) and decoded via the maximum a posteriori (MAP) decoding rule is investigated. It is proved that the ratio of the proba
Externí odkaz:
https://doaj.org/article/fb69d674030443019c93d1390b34b41a
Publikováno v:
Entropy, Vol 24, Iss 10, p 1417 (2022)
Two Rényi-type generalizations of the Shannon cross-entropy, the Rényi cross-entropy and the Natural Rényi cross-entropy, were recently used as loss functions for the improved design of deep learning generative adversarial networks. In this work,
Externí odkaz:
https://doaj.org/article/7480e5a9a37747d290c20f69132c5798
Publikováno v:
Information, Vol 7, Iss 1, p 15 (2016)
A privacy-constrained information extraction problem is considered where for a pair of correlated discrete random variables (X,Y) governed by a given joint distribution, an agent observes Y and wants to convey to a potentially public user as much inf
Externí odkaz:
https://doaj.org/article/888b0cb927b546ebb3423d4069a74200
Publikováno v:
SIAM Journal on Control and Optimization. 60:S347-S369
Publikováno v:
IEEE Control Systems Letters. 6:2780-2785
Publikováno v:
2022 IEEE International Symposium on Information Theory (ISIT).
Publikováno v:
Neural Computation. 33:802-826
Our work focuses on unsupervised and generative methods that address the following goals: (a) learning unsupervised generative representations that discover latent factors controlling image semantic attributes, (b) studying how this ability to contro
We develop a novel method for ensuring fairness in machine learning which we term as the Renyi Fair Information Bottleneck (RFIB). We consider two different fairness constraints - demographic parity and equalized odds - for learning fair representati
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2bab5962f70f458fd68a1c15874298aa
http://arxiv.org/abs/2203.04950
http://arxiv.org/abs/2203.04950
The Rényi cross-entropy measure between two distributions, a generalization of the Shannon cross-entropy, was recently used as a loss function for the improved design of deep learning generative adversarial networks. In this work, we examine the pro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6266ee4463636c923b281538d091dc7d