Results 11 to 20 of about 247,960 (211)

ViT-AE++: Improving Vision Transformer Autoencoder for Self-supervised Medical Image Representations [PDF]

CoRR, 2023
Self-supervised learning has attracted increasing attention as it learns data-driven representation from data without annotations. Vision transformer-based autoencoder (ViT-AE) by He et al.
Wiestler, Benedikt; https://orcid.org/, Yang, Jiancheng, Prabhakar, Chinmay; https://orcid.org/, Menze, Bjoern; https://orcid.org/, Li, Hongwei, Shit, Suprosanna; https://orcid.org/   +5 more
core   +6 more sources

PCA-AE: Principal Component Analysis Autoencoder for Organising the Latent Space of Generative Networks

Journal of Mathematical Imaging and Vision, 2022
International audienceAutoencoders and generative models produce some of the most spectacular deep learning results to date. However, understanding and controlling the latent space of these models presents a considerable challenge.
Ladjal, Saïd, Pham, Chi-Hieu, Newson, Alasdair   +2 more
core   +2 more sources

An Improved Autoencoder and Partial Least Squares Regression-Based Extreme Learning Machine Model for Pump Turbine Characteristics

Applied Sciences, 2019
Complete characteristic curves of a pump turbine are fundamental for improving the modeling accuracy of the pump turbine in a pump turbine governing system.
Chu Zhang, Tian Peng, Jianzhong Zhou, Jie Ji, Xiaolu Wang   +4 more
doaj   +2 more sources

AE-CGAN Model based High Performance Network Intrusion Detection System

Applied Sciences, 2019
In this paper, a high-performance network intrusion detection system based on deep learning is proposed for situations in which there are significant imbalances between normal and abnormal traffic.
JooHwa Lee, KeeHyun Park
doaj   +2 more sources

SPDNet-AE: a Compact SPD Representation through Riemannian Autoencoding

ESANN 2026 proceesdings
International audienceWhen building dimension reduction methods tailored for Symmetric Positive Definite (SPD) matrices, it is crucial to account for their Riemannian geometry. In this work, we propose an SPDNet-based autoencoder, that we call SPDNet-AE,
Yger, Florian, de Surrel, Thibault, Boucherie, Charlotte   +2 more
core   +6 more sources

Orthogonal Matrix-Autoencoder-Based Encoding Method for Unordered Multi-Categorical Variables with Application to Neural Network Target Prediction Problems

Applied Sciences
Neural network models, such as BP, LSTM, etc., support only numerical inputs, so data preprocessing needs to be carried out on the categorical variables to convert them into numerical data.
Yiying Wang, Jinghua Li, Boxin Yang, Dening Song, Lei Zhou   +4 more
doaj   +2 more sources

MLP-Mixer-Autoencoder: A Lightweight Ensemble Architecture for Malware Classification

Information, 2023
Malware is becoming an effective support tool not only for professional hackers but also for amateur ones. Due to the support of free malware generators, anyone can easily create various types of malicious code.
Tuan Van Dao, Hiroshi Sato, Masao Kubo
doaj   +2 more sources

SVD-AE: Simple Autoencoders for Collaborative Filtering [PDF]

CoRR
Collaborative filtering (CF) methods for recommendation systems have been extensively researched, ranging from matrix factorization and autoencoder-based to graph filtering-based methods. Recently, lightweight methods that require almost no training have
Choi, Jeongwhan, Kumar, Srijan, Lee, Yeon-Chang, Hong, Seoyoung, Park, Noseong   +4 more
core   +5 more sources

Multi-Prior Graph Autoencoder with Ranking-Based Band Selection for Hyperspectral Anomaly Detection

Remote Sensing, 2023
Hyperspectral anomaly detection (HAD) is an important technique used to identify objects with spectral irregularity that can contribute to object-based image analysis.
Nan Wang, Yuetian Shi, Haiwei Li, Geng Zhang, Siyuan Li, Xuebin Liu   +5 more
doaj   +2 more sources

An Analysis of Image Classification Using Wavelet-Based Autoencoder Architecture and Extreme Learning Machine

Journal of Electrical and Computer Engineering
In recent machine learning applications, promising outcomes have emerged through the integration of Deep Learning (DL) and Extreme Learning Machine (ELM) techniques with wavelet networks (WN), leading to high classification accuracy.
Salwa Said, Salima Hassairi, Siwar Yahia, Ridha Ejbali, Mourad Zaied   +4 more
doaj   +2 more sources