Shallow Sparsely-Connected Autoencoders for Gene Set Projection by Gold, Maxwell P., Lenail, Alexander, Fraenkel, Ernest

“…Methods exist for identifying gene sets that are differential between conditions, but large public datasets from consortium projects and single-cell RNA-Sequencing have opened the door for gene set analysis using more sophisticated machine learning techniques, such as autoencoders and variational autoencoders. We present shallow sparsely-connected autoencoders (SSCAs) and variational autoencoders (SSCVAs) as tools for projecting gene-level data onto gene sets. …”
Get full text

Event generation and statistical sampling for physics with deep generative models and a density information buffer by Sydney Otten, Sascha Caron, Wieske de Swart, Melissa van Beekveld, Luc Hendriks, Caspar van Leeuwen, Damian Podareanu, Roberto Ruiz de Austri, Rob Verheyen

“…Here, the authors report buffered-density variational autoencoders for the generation of physical events. …”
Get full text

Deciphering protein evolution and fitness landscapes with latent space models by Xinqiang Ding, Zhengting Zou, Charles L. Brooks III

“…Here, the authors demonstrate the utility of latent space models learned using variational autoencoders to infer these properties from sequences.…”
Get full text

Latent generative landscapes as maps of functional diversity in protein sequence space by Cheyenne Ziegler, Jonathan Martin, Claude Sinner, Faruck Morcos

“…Abstract Variational autoencoders are unsupervised learning models with generative capabilities, when applied to protein data, they classify sequences by phylogeny and generate de novo sequences which preserve statistical properties of protein composition. …”
Get full text

Better latent spaces for better autoencoders by Barry M. Dillon, Tilman Plehn, Christof Sauer, Peter Sorrenson

“…To address this, we derive classifiers from the latent space of (variational) autoencoders, specifically in Gaussian mixture and Dirichlet latent spaces. …”
Get full text

Deep learning-based lymphocyte infiltration detection on pathological images by ZHUANG Han, HU Weigang, ZHANG Zhen, WANG Jiazhou

“…This study aimed to assess the performance of using variational autoencoding pre-training method for lymphocyte infiltration detection on pathological images, as well as the impact of removing tumor necrosis regions on model performance. …”
Get full text

Data-Dependent Conditional Priors for Unsupervised Learning of Multimodal Data by 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. …”
Get full text

Generative methods for sampling transition paths in molecular dynamics by Lelièvre Tony, Robin Geneviève, Sekkat Innas, Stoltz Gabriel, Cardoso Gabriel Victorino

“…In view of the promises of machine learning techniques, we explore in this work two approaches to more efficiently generate transition paths: sampling methods based on generative models such as variational autoencoders, and importance sampling methods based on reinforcement learning.…”
Get full text

MONITORING DATA AGGREGATION OF DYNAMIC SYSTEMS USING INFORMATION TECHNOLOGIES by Dmytro Shevchenko, Mykhaylo Ugryumov, Sergii Artiukh

“…Obtained results: the work presents a classification of models and methods for dimensionality reduction, general reviews of vanilla and variational autoencoders, which include a description of the models, their properties, loss functions and their application to the problem of dimensionality reduction. …”
Get full text

siVAE: interpretable deep generative models for single-cell transcriptomes by Yongin Choi, Ruoxin Li, Gerald Quon

“…Abstract Neural networks such as variational autoencoders (VAE) perform dimensionality reduction for the visualization and analysis of genomic data, but are limited in their interpretability: it is unknown which data features are represented by each embedding dimension. …”
Get full text

Direct optimization through arg max for discrete variational auto-encoder by Gane, Andreea, Jaakkola, Tommi S

“…We demonstrate empirically the effectiveness of the direct loss minimization technique in variational autoencoders with both unstructured and structured discrete latent variables.…”
Get full text

Interpreting lion behaviour with nonparametric probabilistic programs by Dhir, N, Wood, F, Vakar, M, Markham, A, Wijers, M, Trethowan, P, Du Preez, B, Loveridge, A, Macdonald, D

“…Furthermore, we combine this approach with unsupervised feature learning, using variational autoencoders.…”

Preliminary Study of Airfoil Design Synthesis Using a Conditional Diffusion Model and Smoothing Method by Kazuo Yonekura, Yuta Oshima, Masaatsu Aichi

“…Generative models such as generative adversarial networks and variational autoencoders are widely used for design synthesis. …”
Get full text

Deep learning for visualization and novelty detection in large X-ray diffraction datasets by Lars Banko, Phillip M. Maffettone, Dennis Naujoks, Daniel Olds, Alfred Ludwig

“…Abstract We apply variational autoencoders (VAE) to X-ray diffraction (XRD) data analysis on both simulated and experimental thin-film data. …”
Get full text

MichiGAN: sampling from disentangled representations of single-cell data using generative adversarial networks by Hengshi Yu, Joshua D. Welch

“…Abstract Deep generative models such as variational autoencoders (VAEs) and generative adversarial networks (GANs) generate and manipulate high-dimensional images. …”
Get full text

Quasi anomalous knowledge: searching for new physics with embedded knowledge by Sang Eon Park, Dylan Rankin, Silviu-Marian Udrescu, Mikaeel Yunus, Philip Harris

“…In this paper, we apply QUAK to anomaly detection of new physics events at the CERN Large Hadron Collider utilizing variational autoencoders with normalizing flow.…”
Get full text

scCross: a deep generative model for unifying single-cell multi-omics with seamless integration, cross-modal generation, and in silico exploration by Xiuhui Yang, Koren K. Mann, Hao Wu, Jun Ding

“…We introduce scCross, a tool leveraging variational autoencoders, generative adversarial networks, and the mutual nearest neighbors (MNN) technique for modality alignment. …”
Get full text

ChemTS: an efficient python library for de novo molecular generation by Xiufeng Yang, Jinzhe Zhang, Kazuki Yoshizoe, Kei Terayama, Koji Tsuda

“…Recently, deep neural network models such as variational autoencoders and recurrent neural networks (RNNs) are shown to be effective in de novo design of molecules without any predetermined fragments. …”
Get full text

Benefits from Variational Regularization in Language Models by Cornelia Ferner, Stefan Wegenkittl

“…In analogy with variational autoencoders, we suggest applying a token-level variational loss to a Transformer architecture and optimizing the standard deviation of the prior distribution in the loss function as the model parameter to increase isotropy. …”
Get full text

Multi-Modal Sentiment Classification With Independent and Interactive Knowledge via Semi-Supervised Learning by Dong Zhang, Shoushan Li, Qiaoming Zhu, Guodong Zhou

“…The key idea is to leverage the semi-supervised variational autoencoders to mine more information from unlabeled data for multi-modal sentiment analysis. …”
Get full text