Results 271 to 280 of about 13,735 (297)

Multi-Task Trajectory Prediction Using a Vehicle-Lane Disentangled Conditional Variational Autoencoder. [PDF]

Sensors (Basel)
Chen H, Li N, Shan H, Liu E, Xiang Z.
europepmc   +1 more source

Multi-objective drug design with a scaffold-aware variational autoencoder. [PDF]

Chem Sci
Dong T, You L, Chen CY.
europepmc   +1 more source

Dirichlet Variational Autoencoder [PDF]

Pattern Recognition, 2020
This paper proposes Dirichlet Variational Autoencoder (DirVAE) using a Dirichlet prior for a continuous latent variable that exhibits the characteristic of the categorical probabilities. To infer the parameters of DirVAE, we utilize the stochastic gradient method by approximating the Gamma distribution, which is a component of the Dirichlet ...
Sungrae Park, Il Chul Moon, Weonyoung Joo   +2 more
exaly   +3 more sources

Hybrid variational autoencoder for time series forecasting [PDF]

Knowledge-Based Systems, 2023
Variational autoencoders (VAE) are powerful generative models that learn the latent representations of input data as random variables. Recent studies show that VAE can flexibly learn the complex temporal dynamics of time series and achieve more promising
Borui Cai, Longxiang Gao, Shuiqiao Yang   +2 more
exaly   +5 more sources

Some of the next articles are maybe not open access.

Related searches:

Mixture variational autoencoders

Pattern Recognition Letters, 2019
Abstract Variational autoencoders (VAEs) combine a generative model and a recognition model, and jointly train them to maximize a variational lower bound. VAEs play an important role in unsupervised learning and representation learning. But the isotropic generative model in VAEs cannot sufficiently utilize the latent representative space.
Shuoran Jiang, Yarui Chen, Jucheng Yang 0001, Chuanlei Zhang, Tingting Zhao 0001   +4 more
openaire   +1 more source

Affine Variational Autoencoders

2019
Variational autoencoders (VAEs) have in recent years become one of the most powerful approaches to learning useful latent representations of data in an unsupervised manner. However, a major challenge with VAEs is that they have tremendous difficulty in generalizing to data that deviate from the training set (e.g., perturbed image variants).
Rene Bidart, Alexander Wong
openaire   +1 more source

Autoencoders and variational autoencoders

2022
openaire   +1 more source

Anomaly detection for multivariate times series through the multi-scale convolutional recurrent variational autoencoder

Expert Systems With Applications, 2023
Qifa Xu, Cuixia Jiang, Tianming Xie
exaly  

Crash data augmentation using variational autoencoder

Accident Analysis and Prevention, 2021
Mohamed Abdel-Aty, Zubayer Islam, Qing Cai   +2 more
exaly