Results 31 to 40 of about 13,513 (170)

ResNet Autoencoders for Unsupervised Feature Learning From High-Dimensional Data: Deep Models Resistant to Performance Degradation

IEEE Access, 2021
Efficient modeling of high-dimensional data requires extracting only relevant dimensions through feature learning. Unsupervised feature learning has gained tremendous attention due to its unbiased approach, no need for prior knowledge or expensive manual
Chathurika S. Wickramasinghe, Daniel L. Marino, Milos Manic   +2 more
doaj   +1 more source

A Novel Multimodal Deep Image Analysis Model for Predicting Extraction/Non-Extraction Decision. [PDF]

Orthod Craniofac Res
ABSTRACT Objective This study aimed to develop a deep learning model classifier capable of predicting the extraction/non‐extraction binary decision using lateral cephalometric radiographs (LCRs) and intraoral scans (IOS) to serve as an additional decision‐support tool for orthodontists.
Ahmad SI, Olczyk J, Araújo AS, de Moura Medeiros JP, Teixeira VC, Gomes CFA, Magnaguagno MC, Roederer Q, Dutra V, Conley RS, Griebler D, Eckert G, Pinho MS, Turkkahraman H.   +13 more
europepmc   +2 more sources

Stacked Denoising Extreme Learning Machine Autoencoder Based on Graph Embedding for Feature Representation

IEEE Access, 2019
Extreme learning machine is characterized by less training parameters, fast training speed, and strong generalization ability. It has been applied to obtain feature representations from the complex data in the tasks of data clustering or classification ...
Hongwei Ge, Weiting Sun, Mingde Zhao, Yao Yao   +3 more
doaj   +1 more source

Missing-Insensitive Short-Term Load Forecasting Leveraging Autoencoder and LSTM

IEEE Access, 2020
In most deep learning-based load forecasting, an intact dataset is required. Since many real-world datasets contain missing values for various reasons, missing imputation using deep learning is actively studied.
Kyungnam Park, Jaeik Jeong, Dongjoo Kim, Hongseok Kim   +3 more
doaj   +1 more source

Scalable and Interpretable One-class SVMs with Deep Learning and Random Fourier features

, 2018
One-class support vector machine (OC-SVM) for a long time has been one of the most effective anomaly detection methods and extensively adopted in both research as well as industrial applications.
A Zimek, CC Chang, D Baehrens, DM Tax, EJ Candès, FE Grubbs, G Montavon, J Kim, JJ Hull, R Chalapathy, S Shalev-Shwartz, SM Erfani, T Schlegl, V Barnett, V Chandola, Y Bengio   +15 more
core   +1 more source

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

, 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. (2021) is a recent self-supervised learning technique that employs a patch-masking strategy to learn a meaningful latent space. In this paper, we focus on improving
Prabhakar, Chinmay, Li, Hongwei, Yang, Jiancheng, Shit, Suprosanna, Wiestler, Benedikt, Menze, Bjoern   +5 more
openaire   +2 more sources

Health Prognostics Classification with Autoencoders for Predictive Maintenance of HVAC Systems

Energies, 2023
Buildings’ heating, ventilation, and air-conditioning (HVAC) systems account for significant global energy use. Proper maintenance can minimize their environmental footprint and enhance the quality of the indoor environment.
Ruiqi Tian, Santiago Gomez-Rosero, Miriam A. M. Capretz   +2 more
doaj   +1 more source

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   +1 more source

Robust, Deep and Inductive Anomaly Detection

, 2017
PCA is a classical statistical technique whose simplicity and maturity has seen it find widespread use as an anomaly detection technique. However, it is limited in this regard by being sensitive to gross perturbations of the input, and by seeking a ...
Chalapathy, Raghavendra, Chawla, Sanjay, Menon, Aditya Krishna   +2 more
core   +1 more source

Hyperspectral anomaly detection via memory‐augmented autoencoders

CAAI Transactions on Intelligence Technology, 2023
Recently, the autoencoder (AE) based method plays a critical role in the hyperspectral anomaly detection domain. However, due to the strong generalised capacity of AE, the abnormal samples are usually reconstructed well along with the normal background ...
Zhe Zhao, Bangyong Sun
doaj   +1 more source