Results 71 to 80 of about 4,772,239 (326)
Variational Laplace Autoencoders
CoRR, 2022 Variational autoencoders employ an amortized inference model to approximate the posterior of latent variables. However, such amortized variational inference faces two challenges: (1) the limited posterior expressiveness of fully-factorized Gaussian assumption and (2) the amortization error of the inference model.
Yookoon S. Park +2 more
openaire +4 more sources
Variational Autoencoder With Optimizing Gaussian Mixture Model Priors
IEEE Access, 2020 The latent variable prior of the variational autoencoder (VAE) often utilizes a standard Gaussian distribution because of the convenience in calculation, but has an underfitting problem.
Chunsheng Guo +5 more
doaj +1 more source
Protein Ensemble Generation Through Variational Autoencoder Latent Space Sampling
bioRxiv, 2023 Mapping the ensemble of protein conformations that contribute to function and can be targeted by small molecule drugs remains an outstanding challenge. Here we explore the use of soft-introspective variational autoencoders for reducing the challenge of ...
Sanaa Mansoor +4 more
semanticscholar +1 more source
Epitomic Variational Graph Autoencoder [PDF]
2020 25th International Conference on Pattern Recognition (ICPR), 2021 Variational autoencoder (VAE) is a widely used generative model for learning latent representations. Burda et al. in their seminal paper showed that learning capacity of VAE is limited by over-pruning. It is a phenomenon where a significant number of latent variables fail to capture any information about the input data and the corresponding hidden ...
Rayyan Ahmad Khan +2 more
openaire +2 more sources
Variational autoencoder and latent space observation tasks
, 2023 Variational autoencoder is an innovation in the field of unsupervised machine learning. Its architecture combines stochastic encoder-decoder modules and deep learning.
Faltejsek, Tomáš
core +1 more source
Adversarial Attention-Based Variational Graph Autoencoder
IEEE Access, 2020 Autoencoders have been successfully used for graph embedding, and many variants have been proven to effectively express graph data and conduct graph analysis in low-dimensional space.
Ziqiang Weng, Weiyu Zhang, Wei Dou
doaj +1 more source
Symbolic expression generation via variational auto-encoder [PDF]
PeerJ Computer Science, 2023 There are many problems in physics, biology, and other natural sciences in which symbolic regression can provide valuable insights and discover new laws of nature. Widespread deep neural networks do not provide interpretable solutions.
Sergei Popov +4 more
doaj +2 more sources
Conditional Variational AutoEncoder based on Stochastic Attack
IACR Cryptology ePrint Archive, 2023 Over the recent years, the cryptanalysis community leveraged the potential of research on Deep Learning to enhance attacks. In particular, several studies have recently highlighted the benefits of Deep Learning based Side-Channel Attacks (DLSCA) to ...
Gabriel Zaid +4 more
semanticscholar +1 more source
Variationally Inferred Sampling through a Refined Bound
Entropy, 2021 In this work, a framework to boost the efficiency of Bayesian inference in probabilistic models is introduced by embedding a Markov chain sampler within a variational posterior approximation.
Víctor Gallego, David Ríos Insua
doaj +1 more source
Business Process Anomaly Detection and Root Cause Analysis Using BLSTM-VAE With Attention
IEEE AccessDetecting anomalous executions in business process data is crucial for safeguarding the efficiency and success of an organization. Unsupervised approaches are commonly used for business process anomaly detection because of the scarcity of labeled anomaly
Eman Abd El-Aziz +3 more
doaj +1 more source