15 papers · ranked by Valyu relevance
Alberto Solera-Rico, Carlos Sanmiguel Vila, Miguel Gómez-López, Yuning Wang + 3 more
'Yuning Wang' 'Abdulrahman Almashjary' 'Scott T. M. Dawson' 'Ricardo Vinuesa'] Variational autoencoder architectures have the potential to develop reduced-order models for chaotic fluid flows. We propose a method for learning compact and near-orthogonal reduced-order models using a combination of a β-variational…
Nicola Milano, Monica Casella, Raffaella Esposito, Davide Marocco + 1 more
'Gianluca Borghini'] 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 methods perform a linear dimensionality reduction…
Aman Singh, Tokunbo Ogunfunmi, Sotiris Kotsiantis
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 Latent Space (which retains the knowledge in the input data with…
Shichen Cao, Jingjing Li, Kenric P. Nelson, Mark A. Kon + 1 more
'Pierre Alquier'] We present a coupled variational autoencoder (VAE) method, which improves the accuracy and robustness of the model representation of handwritten numeral images. The improvement is measured in both increasing the likelihood of the reconstructed images and in reducing divergence between the posterior…
Frantzeska Lavda, Alexandros Kalousis, Sotiris Kotsiantis, Jakub Tomczak
'Jakub Tomczak'] Humans are able to quickly adapt to new situations, learn effectively with limited data, and create unique combinations of basic concepts. In contrast, generalizing out-of-distribution (OOD) data and achieving combinatorial generalizations are fundamental challenges for machine learning models.…
Boopathi Chettiagounder Sengodan, Prince Mary Stanislaus, Sivakumar Sabapathy Arumugam, Dipak Kumar Sah + 6 more
Wireless sensor networks (WSNs) are structured for monitoring an area with distributed sensors and built-in batteries. However, most of their battery energy is consumed during the data transmission process. In recent years, several methodologies, like routing optimization, topology control, and sleep scheduling…
Frantzeska Lavda, Magda Gregorová, Alexandros Kalousis
One of the major shortcomings of variational autoencoders is the inability to produce generations from the individual modalities of data originating from mixture distributions. This is primarily due to the use of a simple isotropic Gaussian as the prior for the latent code in the ancestral sampling procedure for data…
Swapnil Mishra, Seth Flaxman, Tresnia Berah, Harrison Zhu + 2 more
\usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\pi $$\end{document} π VAE: a stochastic process prior for Bayesian deep learning with MCMC Authors: ['Swapnil Mishra'…
Hervé Bourlard, Selen Hande Kabil
In Bourlard and Kamp (Biol Cybern 59(4):291-294, 1998), it was theoretically proven that autoencoders (AE) with single hidden layer (previously called “auto-associative multilayer perceptrons”) were, in the best case, implementing singular value decomposition (SVD) Golub and Reinsch (Linear algebra, Singular value…
Hao Tian, Xi Jiang, Francesco Trozzi, Sian Xiao + 2 more
'Peng Tao'] Molecular dynamics (MD) simulations have been actively used in the study of protein structure and function. However, extensive sampling in the protein conformational space requires large computational resources and takes a prohibitive amount of time. In this study, we demonstrated that variational…
Sergei Popov, Mikhail Lazarev, Vladislav Belavin, Denis Derkach + 2 more
'Andrey Ustyuzhanin' 'Muhammad Aleem'] 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. Meanwhile, symbolic expressions give us a…
Nicolas Vercheval, Remco Royen, Adrian Munteanu, Aleksandra Pižurica + 1 more
Generative models have the potential to revolutionize 3D extended reality. A primary obstacle is that augmented and virtual reality need real-time computing. Current state-of-the-art point cloud random generation methods are not fast enough for these applications. We introduce a vector-quantized variational autoencoder…
Vignesh Sampath, Iñaki Maurtua, Juan José Aguilar Martín, Aitor Gutierrez
Any computer vision application development starts off by acquiring images and data, then preprocessing and pattern recognition steps to perform a task. When the acquired images are highly imbalanced and not adequate, the desired task may not be achievable. Unfortunately, the occurrence of imbalance problems in…
Sara Rajaram, Cassie S. Mitchell
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 framework to conduct data augmentation in a cross-modal dataset by…
María Teresa García-Ordás, José Alberto Benítez-Andrades, Isaías García-Rodríguez, Carmen Benavides + 1 more
'Isaías García-Rodríguez' 'Carmen Benavides' 'Héctor Alaiz-Moretón'] 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…