Interpretable Models in Probabilistic Machine Learning by Kim, H

“…Third, we introduce a Variational Autoencoder (VAE) model that can disentangle independent factors of variations in a dataset of images by learning a factorisable latent distribution in an unsupervised fashion. …”

A Statistical Comparative Study on Image Reconstruction and Clustering With Novel VAE Cost Function by Alla Abdella, Ismail Uysal

“…First, we conduct an extensive and first-of-its-kind empirical study on the statistical relationship between the clustering accuracy and image reconstruction quality of a state-of-the-art deep clustering topology in the form of a convolutional variational autoencoder (VAE) with a K-means back end. We change the latent variable z at the bottleneck of the network to create different latent dimensions and explore how clustering performance metrics and reconstruction metrics are statistically related. …”
Get full text

Intelligent Generation of Cross Sections Using a Conditional Generative Adversarial Network and Application to Regional 3D Geological Modeling by Xiangjin Ran, Linfu Xue, Xuejia Sang, Yao Pei, Yanyan Zhang

“…The results show that: (a) the accuracy of the proposed method is higher than the GAN and Variational AutoEncoder (VAE) models, achieving 87%, 45% and 68%, respectively; (b) the 3D geological model constructed by the generated cross sections in our study is consistent with manual creation in terms of stratum continuity and thickness. …”
Get full text

Digit Recognition Based on Specialization, Decomposition and Holistic Processing by Michael Joseph, Khaled Elleithy

“…The model uses a variational autoencoder to generate holistic representation of handwritten digits and a Neural Network(NN) to classify them. …”
Get full text

Recommendation Method for Time-Sequence Point of Interest via Spatio-Temporal Vicinity Perception by WEN Wen, DENG Fengying, HAO Zhifeng, CAI Ruichu, LIANG Fangyu

“…Firstly, the variational autoencoder is utilized to represent the potential state of users. …”
Get full text

Multimodal few-shot classification without attribute embedding by Jun Qing Chang, Deepu Rajan, Nicholas Vun

“…The model consists of a variational autoencoder to learn the visual latent representation, which is combined with a semantic latent representation that is learnt from a normal autoencoder, which calculates a semantic loss between the latent representation and a binary attribute vector. …”
Get full text

PaccMannRL: De novo generation of hit-like anticancer molecules from transcriptomic data via reinforcement learning by Jannis Born, Matteo Manica, Ali Oskooei, Joris Cadow, Greta Markert, María Rodríguez Martínez

“…We construct a hybrid Variational Autoencoder that tailors molecules to target-specific transcriptomic profiles, using an anticancer drug sensitivity prediction model (PaccMann) as reward function. …”
Get full text

Orientation-invariant autoencoders learn robust representations for shape profiling of cells and organelles by James Burgess, Jeffrey J. Nirschl, Maria-Clara Zanellati, Alejandro Lozano, Sarah Cohen, Serena Yeung-Levy

“…To address this, we develop O2-variational autoencoder (O2-VAE), an unsupervised method that learns robust, orientation-invariant representations. …”
Get full text

Real‐time out‐of‐distribution detection in cyber‐physical systems with learning‐enabled components by Feiyang Cai, Xenofon Koutsoukos

“…Specifically, variational autoencoder and deep support vector data description networks are used to learn models for the real‐time detection of out‐of‐distribution high‐dimensional inputs. …”
Get full text

Symbolic expression generation via variational auto-encoder by Sergei Popov, Mikhail Lazarev, Vladislav Belavin, Denis Derkach, Andrey Ustyuzhanin

“…In this work, we propose a novel deep learning framework for symbolic expression generation via variational autoencoder (VAE). We suggest using a VAE to generate mathematical expressions, and our training strategy forces generated formulas to fit a given dataset. …”
Get full text

Malware Identification Method in Industrial Control Systems Based on Opcode2vec and CVAE-GAN by Yuchen Huang, Jingwen Liu, Xuanyi Xiang, Pan Wen, Shiyuan Wen, Yanru Chen, Liangyin Chen, Yuanyuan Zhang

“…Our method integrates the opcode2vec method based on preprocessed features with a conditional variational autoencoder–generative adversarial network, enabling classifiers based on Convolutional Neural Networks to identify malware more effectively and with some degree of increased stability and robustness. …”
Get full text

Inferring colloidal interaction from scattering by machine learning by Chi-Huan Tung, Shou-Yi Chang, Ming-Ching Chang, Jan-Michael Carrillo, Bobby G Sumpter, Changwoo Do, Wei-Ren Chen

“…The inversion scheme consists of two major components, a generative network featuring a variational autoencoder which extracts the targeted static two-point correlation functions from experimentally measured scattering cross sections, and a Gaussian process framework which probabilistically infers the relevant structural parameters from the inverted correlation functions. …”
Get full text

Central Kurdish Text-to-Speech Synthesis with Novel End-to-End Transformer Training by Hawraz A. Ahmad, Tarik A. Rashid

“…The proposed method leverages a variational autoencoder (VAE) that is pre-trained for audio waveform reconstruction and is augmented by adversarial training. …”
Get full text

Robust real-time imaging through flexible multimode fibers by Abdullah Abdulaziz, Simon Peter Mekhail, Yoann Altmann, Miles J. Padgett, Stephen McLaughlin

“…We leverage a variational autoencoder to reconstruct and classify images from the speckles and show that these images can still be recovered when the bend configuration of the fiber is changed to one that was not part of the training set. …”
Get full text

Prairie Dog Optimization Algorithm with deep learning assisted based Aerial Image Classification on UAV imagery by Amal K. Alkhalifa, Muhammad Kashif Saeed, Kamal M. Othman, Shouki A. Ebad, Mohammed Alonazi, Abdullah Mohamed

“…The PDODL-AICA technique uses a convolutional variational autoencoder (CVAE) model to detect and classify aerial images. …”
Get full text

IoT Anomaly Detection to Strengthen Cybersecurity in the Critical Infrastructure of Smart Cities by William Villegas-Ch, Jaime Govea, Angel Jaramillo-Alcazar

“…The results show that the proposed models, including Isolation Forest, recurrent neural network, and variational autoencoder, are highly effective in detecting anomalies in urban data. …”
Get full text

iVAE-GAN: Identifiable VAE-GAN Models for Latent Representation Learning by Bjorn Uttrup Dideriksen, Kristoffer Derosche, Zheng-Hua Tan

“…We extend the family of identifiable models by proposing an identifiable Variational Autoencoder (VAE) based Generative Adversarial Network (GAN) model we name iVAE-GAN. …”
Get full text

Generative Data‐Driven Approaches for Stochastic Subgrid Parameterizations in an Idealized Ocean Model by Pavel Perezhogin, Laure Zanna, Carlos Fernandez‐Granda

“…Here, we aim to improve the simulation of stochastic forcing with generative models of ML, such as Generative adversarial network (GAN) and Variational autoencoder (VAE). Generative models learn the distribution of subgrid forcing conditioned on the resolved flow directly from data and they can produce new samples from this distribution. …”
Get full text

Generative Adversarial Networks GAN Overview by LIANG Junjie, WEI Jianjing, JIANG Zhengfeng

“…At the same time, this paper compares GAN with VAE (variational autoencoder) and RBM (restricted Boltzmann machine) models, and summarizes the advantages and disadvantages of GAN. …”
Get full text

Adversarially Learned Total Variability Embedding for Speaker Recognition with Random Digit Strings by Woo Hyun Kang, Nam Soo Kim

“…Analogous to the previously proposed variational autoencoder (VAE)-based feature extractor, the proposed ALI-based model is trained to generate the GMM supervector according to the maximum likelihood criterion given the Baum−Welch statistics of the input utterance. …”
Get full text