Skip to Content

971 Results Found

  • Review
  • Open Access
3 Citations
3,793 Views
48 Pages

28 February 2026

This tutorial provides a comprehensive and intuitive journey through the evolution of deep generative models, tracing a clear path from the foundations of Principal Component Analysis (PCA) to modern Variational Autoencoders (VAEs), showing how each...

(This article belongs to the Section Data Science, Machine Learning and Artificial Intelligence)
  • Article
  • Open Access
20 Citations
5,121 Views
24 Pages

A Bayesian Nonlinear Reduced Order Modeling Using Variational AutoEncoders

  • Nissrine Akkari,
  • Fabien Casenave,
  • Elie Hachem and
  • David Ryckelynck

20 October 2022

This paper presents a new nonlinear projection based model reduction using convolutional Variational AutoEncoders (VAEs). This framework is applied on transient incompressible flows. The accuracy is obtained thanks to the expression of the velocity a...

(This article belongs to the Special Issue Next-Generation Methods for Turbulent Flows)
  • Feature Paper
  • Article
  • Open Access
229 Views
29 Pages

9 October 2026

Among other uses, neural networks are used to solve deterministic and Bayesian inverse problems, where variational autoencoders enable the Bayesian estimation of model parameters and their distribution from observational data allowing real-time inver...

(This article belongs to the Section E1: Mathematics and Computer Science)
  • Article
  • Open Access
3 Citations
5,711 Views
22 Pages

Variational Autoencoders for Completing the Volatility Surfaces

  • Bienvenue Feugang Nteumagné,
  • Hermann Azemtsa Donfack and
  • Celestin Wafo Soh

Variational autoencoders (VAEs) have emerged as a promising tool for modeling volatility surfaces, with particular significance for generating synthetic implied volatility scenarios that enhance risk management capabilities. This study evaluates VAE...

(This article belongs to the Special Issue Machine Learning-Based Risk Management in Finance and Insurance)
  • Review
  • Open Access
95 Citations
16,237 Views
55 Pages

28 December 2021

Autoencoders are a self-supervised learning system where, during training, the output is an approximation of the input. Typically, autoencoders have three parts: Encoder (which produces a compressed latent space representation of the input data), the...

(This article belongs to the Special Issue Adaptive Signal Processing and Machine Learning Using Entropy and Information Theory)
  • Article
  • Open Access
6 Citations
5,657 Views
16 Pages

9 August 2022

In natural language processing (NLP), Transformer is widely used and has reached the state-of-the-art level in numerous NLP tasks such as language modeling, summarization, and classification. Moreover, a variational autoencoder (VAE) is an efficient...

(This article belongs to the Special Issue Application of Machine Learning in Text Mining)
  • Article
  • Open Access
44 Citations
5,977 Views
16 Pages

An Efficient Anomaly Detection System for Crowded Scenes Using Variational Autoencoders

  • Ming Xu,
  • Xiaosheng Yu,
  • Dongyue Chen,
  • Chengdong Wu and
  • Yang Jiang

14 August 2019

Anomaly detection in crowded scenes is an important and challenging part of the intelligent video surveillance system. As the deep neural networks make success in feature representation, the features extracted by a deep neural network represent the a...

  • Article
  • Open Access
7 Citations
2,968 Views
23 Pages

25 June 2024

Latent variables analysis is an important part of psychometric research. In this context, factor analysis and other related techniques have been widely applied for the investigation of the internal structure of psychometric tests. However, these meth...

  • Article
  • Open Access
12 Citations
5,132 Views
22 Pages

24 October 2021

Despite the importance of few-shot learning, the lack of labeled training data in the real world makes it extremely challenging for existing machine learning methods because this limited dataset does not well represent the data variance. In this rese...

  • Article
  • Open Access
296 Views
19 Pages

30 September 2026

Image reconstruction and generation have become fundamental tasks in computer vision and quantum-inspired machine learning. Existing quantum-inspired variational autoencoders have demonstrated promising capabilities; however, they often suffer from l...

(This article belongs to the Section Information Theory and Methodology)
  • Article
  • Open Access
20 Citations
3,973 Views
17 Pages

An Information-Theoretic Perspective on Proper Quaternion Variational Autoencoders

  • Eleonora Grassucci,
  • Danilo Comminiello and
  • Aurelio Uncini

3 July 2021

Variational autoencoders are deep generative models that have recently received a great deal of attention due to their ability to model the latent distribution of any kind of input such as images and audio signals, among others. A novel variational a...

(This article belongs to the Special Issue Adaptive Signal Processing and Machine Learning Using Entropy and Information Theory)
  • Article
  • Open Access
65 Citations
8,612 Views
20 Pages

Variational Autoencoders for Data Augmentation in Clinical Studies

  • Dimitris Papadopoulos and
  • Vangelis D. Karalis

30 July 2023

Sample size estimation is critical in clinical trials. A sample of adequate size can provide insights into a given population, but the collection of substantial amounts of data is costly and time-intensive. The aim of this study was to introduce a no...

(This article belongs to the Section Applied Biosciences and Bioengineering)
  • Review
  • Open Access
332 Views
56 Pages

3 October 2026

Medical image segmentation plays an important role in healthcare because it transforms raw scans into useful information for diagnosis and treatment planning. Despite the strong performance of deep learning, most supervised segmentation methods requi...

(This article belongs to the Special Issue Unified and Multimodal Segmentation: Foundations, Methods, and Applications)
  • Article
  • Open Access
5 Citations
5,251 Views
14 Pages

Classical Music Prediction and Composition by Means of Variational Autoencoders

  • Daniel Rivero,
  • Iván Ramírez-Morales,
  • Enrique Fernandez-Blanco,
  • Norberto Ezquerra and
  • Alejandro Pazos

27 April 2020

This paper proposes a new model for music prediction based on Variational Autoencoders (VAEs). In this work, VAEs are used in a novel way to address two different issues: music representation into the latent space, and using this representation to ma...

(This article belongs to the Special Issue Applied Artificial Neural Networks)
  • Article
  • Open Access
10 Citations
2,134 Views
14 Pages

The world’s population is increasing and so is the challenge on existing healthcare infrastructure to cope with the growing demand in medical diagnosis and evaluation. Although human experts are primarily tasked with the diagnosis of different...

(This article belongs to the Section Machine Learning and Artificial Intelligence in Diagnostics)
  • Article
  • Open Access
2 Citations
706 Views
31 Pages

Fractional Variational Graph Autoencoders for Enhancing Non-Local Representation Learning on Graphs

  • Mohamed Ilyas El Harrak,
  • Omar Bahou,
  • Karim El Moutaouakil,
  • Ahmed Nuino and ,
  • Eddakir Abdellatif and
  • Alina-Mihaela Patriciu
  • + 1 author+ 0 author

While Graph Autoencoders (GAEs) have become a standard for unsupervised representation learning, their reliance on integer-order convolutions inherently restricts information propagation to immediate local neighborhoods. This paper introduces the Fra...

(This article belongs to the Section Artificial Intelligence)
  • Article
  • Open Access
2 Citations
2,838 Views
25 Pages

SIGRN: Inferring Gene Regulatory Network with Soft Introspective Variational Autoencoders

  • Rongyuan Li,
  • Jingli Wu,
  • Gaoshi Li,
  • Jiafei Liu and ,
  • Jinlu Liu,
  • Junbo Xuan and
  • Zheng Deng
  • + 2 authors+ 0 author

27 November 2024

Gene regulatory networks (GRNs) exhibit the complex regulatory relationships among genes, which are essential for understanding developmental biology and uncovering the fundamental aspects of various biological phenomena. It is an effective and econo...

(This article belongs to the Section Molecular Genetics and Genomics)
  • Article
  • Open Access
3 Citations
2,327 Views
14 Pages

We present a conditional variational autoencoder (CVAE) that generates stellar spectra covering 4000 ≤ Teff ≤ 11,000 K, 2.0≤logg≤5.0 dex, −1.5≤[M/H]≤+1.5 dex, vsini≤300 km/s, ξt between 0 and 4 km/s, and for any instrume...

  • Article
  • Open Access
33 Citations
11,371 Views
11 Pages

17 September 2021

In recent years, learning-based approaches for 3D reconstruction have gained much popularity due to their encouraging results. However, unlike 2D images, 3D cannot be represented in its canonical form to make it computationally lean and memory-effici...

(This article belongs to the Special Issue Computer Graphics, Image Processing and Artificial Intelligence)
  • Article
  • Open Access
20 Citations
3,463 Views
14 Pages

25 February 2024

Structural health monitoring (SHM) has become paramount for developing cheaper and more reliable maintenance policies. The advantages coming from adopting such process have turned out to be particularly evident when dealing with plated structures. In...

(This article belongs to the Special Issue Structural Health Monitoring Using Sensors and Machine Learning)
  • Article
  • Open Access
3,735 Views
14 Pages

Graph variational auto-encoder (GVAE) is a model that combines neural networks and Bayes methods, capable of deeper exploring the influential latent features of graph reconstruction. However, several pieces of research based on GVAE employ a plain pr...

  • Article
  • Open Access
31 Citations
4,597 Views
15 Pages

Variational Autoencoders-Based Algorithm for Multi-Criteria Recommendation Systems

  • Salam Fraihat,
  • Qusai Shambour,
  • Mohammed Azmi Al-Betar and
  • Sharif Naser Makhadmeh

8 December 2024

In recent years, recommender systems have become a crucial tool, assisting users in discovering and engaging with valuable information and services. Multi-criteria recommender systems have demonstrated significant value in assisting users to identify...

(This article belongs to the Section Analysis of Algorithms and Complexity Theory)
  • Article
  • Open Access
5 Citations
3,847 Views
15 Pages

On the Use of Kullback–Leibler Divergence for Kernel Selection and Interpretation in Variational Autoencoders for Feature Creation

  • Fábio Mendonça,
  • Sheikh Shanawaz Mostafa,
  • Fernando Morgado-Dias and
  • Antonio G. Ravelo-García

18 October 2023

This study presents a novel approach for kernel selection based on Kullback–Leibler divergence in variational autoencoders using features generated by the convolutional encoder. The proposed methodology focuses on identifying the most relevant...

(This article belongs to the Special Issue Deep Learning for Image, Video and Signal Processing)
  • Article
  • Open Access
361 Views
15 Pages

5 July 2026

Variational autoencoders (VAEs) are sensitive to spatially heterogeneous noise because corrupted high-frequency components can be propagated into the latent posterior and degrade reconstruction. We propose Learnable Local FFT-VAE, a VAE-oriented loca...

  • Article
  • Open Access
9 Citations
4,034 Views
14 Pages

21 December 2023

The ability to translate Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs) into different modalities and data types is essential to improve Deep Learning (DL) for predictive medicine. This work presents DACMVA, a novel framew...

(This article belongs to the Section Biomedical Information and Health)
  • Proceeding Paper
  • Open Access
2 Citations
2,670 Views
9 Pages

The separation of respiratory and cardiac sounds is a significant challenge in biomedical signal processing due to their overlapping frequency and time characteristics. Traditional methods struggle with accurate extraction in noisy or diverse clinica...

(This article belongs to the Proceedings of International Conference on Sustainable Computing and Green Technologies (SCGT’2025))
  • Article
  • Open Access
10 Citations
3,134 Views
20 Pages

Failure Detection in Sensors via Variational Autoencoders and Image-Based Feature Representation

  • Luis Miguel Moreno Haro,
  • Adaiton Oliveira-Filho,
  • Bruno Agard and
  • Antoine Tahan

29 March 2025

This paper presents a novel approach for detecting sensor failures using image-based feature representation and the Convolutional Variational Autoencoder (CVAE) model. Existing methods are limited when analyzing multiple failure modes simultaneously...

(This article belongs to the Special Issue Sensor-Based Fault Detection and Diagnosis in Mechatronic Systems)
  • Article
  • Open Access
25 Citations
4,211 Views
15 Pages

13 May 2022

In railway surface defect detection applications, supervised deep learning methods suffer from the problems of insufficient defect samples and an imbalance between positive and negative samples. To overcome these problems, we propose a lightweight tw...

(This article belongs to the Special Issue Failure and Multiphysical Fields in Geo-Energy)
  • Article
  • Open Access
61 Views
31 Pages

From Narratives to Probable Causes? Evaluating Variational Autoencoders for Aviation Safety Representation Prediction

  • Aziida Nanyonga,
  • Hassan Wasswa,
  • Ugur Turhan,
  • Keith Francis Joiner and
  • Graham Wild

18 November 2026

Aviation accident and incident investigations generate extensive unstructured textual information containing evidence relevant to the causes and contributing factors of safety occurrences. Automatically identifying such information is challenging bec...

  • Article
  • Open Access
113 Citations
9,629 Views
16 Pages

Detecting Respiratory Pathologies Using Convolutional Neural Networks and Variational Autoencoders for Unbalancing Data

  • María Teresa García-Ordás,
  • José Alberto Benítez-Andrades,
  • Isaías García-Rodríguez,
  • Carmen Benavides and
  • Héctor Alaiz-Moretón

22 February 2020

The aim of this paper was the detection of pathologies through respiratory sounds. The ICBHI (International Conference on Biomedical and Health Informatics) Benchmark was used. This dataset is composed of 920 sounds of which 810 are of chronic diseas...

(This article belongs to the Special Issue Sensor and Systems Evaluation for Telemedicine and eHealth)
  • Article
  • Open Access
462 Views
51 Pages

Intrinsic-dimension (ID) estimates and active-unit diagnostics address different aspects of variational-autoencoder bottleneck selection. We evaluate search policies on four image datasets, five training seeds and five regularisation weights under ex...

(This article belongs to the Section Learning)
  • Article
  • Open Access
7 Citations
5,685 Views
21 Pages

Community Detection Using Deep Learning: Combining Variational Graph Autoencoders with Leiden and K-Truss Techniques

  • Jyotika Hariom Patil,
  • Petros Potikas,
  • William B. Andreopoulos and
  • Katerina Potika

16 September 2024

Deep learning struggles with unsupervised tasks like community detection in networks. This work proposes the Enhanced Community Detection with Structural Information VGAE (VGAE-ECF) method, a method that enhances variational graph autoencoders (VGAEs...

(This article belongs to the Special Issue Optimization Algorithms and Their Applications)
  • Article
  • Open Access
1,058 Views
28 Pages

24 April 2025

The machine learning-based approaches for analysing the mobility needs of users are currently the most prevalent approach in the mobility-on-demand (MoD) analysis. Their efficiency relies on the comprehensiveness and consistency of training datasets....

(This article belongs to the Special Issue Intelligent Transportation System Technologies and Applications, 2nd Edition)
  • Article
  • Open Access
18 Citations
5,981 Views
29 Pages

4 March 2021

Two of the biggest challenges in building models for detecting emotions from electroencephalography (EEG) devices are the relatively small amount of labeled samples and the strong variability of signal feature distributions between different subjects...

(This article belongs to the Special Issue Neurophysiological Monitoring)
  • Article
  • Open Access
134 Citations
9,824 Views
19 Pages

Brain tumors are a pernicious cancer with one of the lowest five-year survival rates. Neurologists often use magnetic resonance imaging (MRI) to diagnose the type of brain tumor. Automated computer-assisted tools can help them speed up the diagnosis...

(This article belongs to the Special Issue Artificial Intelligence in Biological and Biomedical Imaging)
  • Article
  • Open Access
16 Citations
7,945 Views
17 Pages

7 April 2025

Driven by rapid advancements in big data and Internet of Things (IoT) technologies, time series data are now extensively utilized across diverse industrial sectors. The precise identification of anomalies in time series data—especially within i...

  • Article
  • Open Access
2 Citations
3,474 Views
31 Pages

Deploying text-to-image (T2I) models is challenging due to high computational demands, extensive data needs, and the persistent goal of enhancing generation quality and diversity, particularly on resource-constrained devices. We introduce a lightweig...

(This article belongs to the Special Issue Big Model Techniques for Image Processing)
  • Article
  • Open Access
3 Citations
814 Views
18 Pages

21 March 2026

A synthetic data generation method is proposed to mitigate data imbalance in pipeline leak detection using acoustic emission (AE) sensors. Collecting sufficient AE signals in the leak state is challenging due to the rarity of leaks and safety concern...

(This article belongs to the Special Issue Recent Developments in Acoustic Emission and Non-Destructive Evaluation)
  • Article
  • Open Access
8 Citations
4,359 Views
19 Pages

4 September 2023

Dimensionality reduction and producing simple representations of electroencephalography (EEG) signals are challenging problems. Variational autoencoders (VAEs) have been employed for EEG data creation, augmentation, and automatic feature extraction....

(This article belongs to the Special Issue Advances in Explainable Artificial Intelligence)
  • Article
  • Open Access
13 Citations
3,886 Views
18 Pages

11 September 2022

Remote sensing image scene classification takes image blocks as classification units and predicts their semantic descriptors. Because it is difficult to obtain enough labeled samples for all classes of remote sensing image scenes, zero-shot classific...

  • Article
  • Open Access
2,703 Views
20 Pages

Generating realistic and diverse driving scenarios is essential for effective scenario-based testing and validation in autonomous driving and the development of driver assistance systems. Traditionally, parametric models are used as standard approach...

(This article belongs to the Special Issue Autonomous Vehicles and Urban Evolution: Technological, Social and Environmental Perspectives)
  • Article
  • Open Access
29 Citations
8,490 Views
21 Pages

7 February 2020

Variational Graph Autoencoder (VGAE) has recently gained traction for learning representations on graphs. Its inception has allowed models to achieve state-of-the-art performance for challenging tasks such as link prediction, rating prediction, and n...

(This article belongs to the Special Issue Computation in Complex Networks)
  • Article
  • Open Access
4 Citations
2,839 Views
19 Pages

Video Colorization Based on Variational Autoencoder

  • Guangzi Zhang,
  • Xiaolin Hong,
  • Yan Liu,
  • Yulin Qian and
  • Xingquan Cai

This paper introduces a variational autoencoder network designed for video colorization using reference images, addressing the challenge of colorizing black-and-white videos. Although recent techniques perform well in some scenarios, they often strug...

(This article belongs to the Special Issue Image/Video Processing and Encoding for Contemporary Applications)
  • Article
  • Open Access
5 Citations
4,131 Views
18 Pages

24 February 2023

In this paper, we propose a sequential variational autoencoder for video disentanglement, which is a representation learning method that can be used to separately extract static and dynamic features from videos. Building sequential variational autoen...

(This article belongs to the Section Intelligent Sensors)
  • Article
  • Open Access
3 Citations
6,508 Views
15 Pages

18 February 2021

Variational graph autoencoder, which can encode structural information and attribute information in the graph into low-dimensional representations, has become a powerful method for studying graph-structured data. However, most existing methods based...

(This article belongs to the Section Big Data and Augmented Intelligence)
  • Article
  • Open Access
1 Citations
1,033 Views
23 Pages

Quantum Down-Sampling Filter for Variational Autoencoder

  • Farina Riaz,
  • Fakhar Zaman,
  • Hajime Suzuki,
  • Alsharif Abuadbba and
  • David Nguyen

25 November 2025

Variational Autoencoders (VAEs) are fundamental for generative modeling and image reconstruction, yet their performance often struggles to maintain high fidelity in reconstructions. This study introduces a hybrid model, Quantum Variational Autoencode...

(This article belongs to the Special Issue Second Quantum Revolution: Sensing, Computing, and Transmitting)
  • Article
  • Open Access
295 Citations
20,989 Views
17 Pages

Conditional Variational Autoencoder for Prediction and Feature Recovery Applied to Intrusion Detection in IoT

  • Manuel Lopez-Martin,
  • Belen Carro,
  • Antonio Sanchez-Esguevillas and
  • Jaime Lloret

26 August 2017

The purpose of a Network Intrusion Detection System is to detect intrusive, malicious activities or policy violations in a host or host’s network. In current networks, such systems are becoming more important as the number and variety of attacks incr...

(This article belongs to the Special Issue Sensor Networks for Collaborative and Secure Internet of Things)
  • Article
  • Open Access
4,967 Views
38 Pages

InvMap and Witness Simplicial Variational Auto-Encoders

  • Aniss Aiman Medbouhi,
  • Vladislav Polianskii,
  • Anastasia Varava and
  • Danica Kragic

Variational auto-encoders (VAEs) are deep generative models used for unsupervised learning, however their standard version is not topology-aware in practice since the data topology may not be taken into consideration. In this paper, we propose two di...

(This article belongs to the Topic Topology vs. Geometry in Data Analysis/Machine Learning)
  • Article
  • Open Access
67 Citations
7,479 Views
27 Pages

Reduced-Complexity End-to-End Variational Autoencoder for on Board Satellite Image Compression

  • Vinicius Alves de Oliveira,
  • Marie Chabert,
  • Thomas Oberlin,
  • Charly Poulliat and ,
  • Mickael Bruno,
  • Christophe Latry,
  • Mikael Carlavan,
  • Simon Henrot,
  • Frederic Falzon and
  • Roberto Camarero
  • + 5 authors+ 0 author

27 January 2021

Recently, convolutional neural networks have been successfully applied to lossy image compression. End-to-end optimized autoencoders, possibly variational, are able to dramatically outperform traditional transform coding schemes in terms of rate-dist...

(This article belongs to the Special Issue Remote Sensing Data Compression)
  • Article
  • Open Access
2 Citations
2,920 Views
18 Pages

Functional Subspace Variational Autoencoder for Domain-Adaptive Fault Diagnosis

  • Tan Li,
  • Che-Heng Fung,
  • Him-Ting Wong,
  • Tak-Lam Chan and
  • Haibo Hu

28 June 2023

This paper presents the functional subspace variational autoencoder, a technique addressing challenges in sensor data analysis in transportation systems, notably the misalignment of time series data and a lack of labeled data. Our technique converts...

(This article belongs to the Special Issue Data-Driven Methods and Artificial Intelligence in Reliability and Maintenance, 2nd Edition)

of 20