Zobrazeno 1 - 10
of 209
pro vyhledávání: '"Khoat Than"'
Publikováno v:
Scientific Reports, Vol 11, Iss 1, Pp 1-16 (2021)
Abstract Predicting beneficial and valuable miRNA–disease associations (MDAs) by doing biological laboratory experiments is costly and time-consuming. Proposing a forceful and meaningful computational method for predicting MDAs is essential and cap
Externí odkaz:
https://doaj.org/article/44c85399420a42a7917512a7d0f57c98
Publikováno v:
IEEE Access, Vol 8, Pp 106395-106407 (2020)
In this work, we focus on dealing with a sparse users' feedback matrix and short descriptions/contents of items in recommender systems. We propose the Neural Poisson factorization (NPF) model which is a hybrid of deep learning and Poisson factorizati
Externí odkaz:
https://doaj.org/article/3fa5bcc93c4a4f74b268b25d65ef2d66
Publikováno v:
IEEE Access, Vol 8, Pp 127818-127833 (2020)
MAP estimation plays an important role in many probabilistic models. However, in many cases, the MAP problem is non-convex and intractable. In this work, we propose a novel algorithm, called BOPE, which uses Bernoulli randomness for Online Maximum a
Externí odkaz:
https://doaj.org/article/08395ab6e8cf44dbac47daeb076647f5
Denoising Probabilistic Models (DPMs) represent an emerging domain of generative models that excel in generating diverse and high-quality images. However, most current training methods for DPMs often neglect the correlation between timesteps, limitin
Externí odkaz:
http://arxiv.org/abs/2312.12431
Online Class Incremental learning (CIL) is a challenging setting in Continual Learning (CL), wherein data of new tasks arrive in incoming streams and online learning models need to handle incoming data streams without revisiting previous ones. Existi
Externí odkaz:
http://arxiv.org/abs/2211.16780
We propose a novel high-fidelity face swapping method called "Arithmetic Face Swapping" (AFS) that explicitly disentangles the intermediate latent space W+ of a pretrained StyleGAN into the "identity" and "style" subspaces so that a latent code in W+
Externí odkaz:
http://arxiv.org/abs/2211.10812
Publikováno v:
In Neurocomputing 28 August 2024 595
In this work, we examine the advantages of using multiple types of behaviour in recommendation systems. Intuitively, each user has to do some implicit actions (e.g., click) before making an explicit decision (e.g., purchase). Previous studies showed
Externí odkaz:
http://arxiv.org/abs/2107.12325
Autor:
Than, Khoat, Vu, Nghia
Generative adversarial networks (GANs) are so complex that the existing learning theories do not provide a satisfactory explanation for why GANs have great success in practice. The same situation also remains largely open for deep neural networks. To
Externí odkaz:
http://arxiv.org/abs/2104.02388
Approximate inference in Bayesian deep networks exhibits a dilemma of how to yield high fidelity posterior approximations while maintaining computational efficiency and scalability. We tackle this challenge by introducing a novel variational structur
Externí odkaz:
http://arxiv.org/abs/2102.07927