Results 61 to 70 of about 341,780 (320)
Semi-Supervised Learning for Neural Machine Translation
, 2016 While end-to-end neural machine translation (NMT) has made remarkable progress recently, NMT systems only rely on parallel corpora for parameter estimation. Since parallel corpora are usually limited in quantity, quality, and coverage, especially for low-
Cheng, Yong +6 more
core +1 more source
Arthritis Care &Research, Accepted Article.Systemic sclerosis (SSc) is a rare autoimmune disease defined by immune dysregulation, vasculopathy, and progressive fibrosis of the skin and internal organs. Despite advances in care, major complications such as interstitial lung disease (ILD) and myocardial involvement remain the leading causes of morbidity and mortality.
Cristiana Sieiro Santos +2 more
wiley +1 more source
Graph Laplacian for Semi-supervised Learning
, 2023 Semi-supervised learning is highly useful in common scenarios where labeled data is scarce but unlabeled data is abundant. The graph (or nonlocal) Laplacian is a fundamental smoothing operator for solving various learning tasks. For unsupervised clustering, a spectral embedding is often used, based on graph-Laplacian eigenvectors.
Streicher, Or, Gilboa, Guy
openaire +2 more sources
A Knowledge‐Based Approach for Understanding and Managing Additive Manufacturing Data
Advanced Engineering Materials, EarlyView.Additive manufacturing processes generate a large amount of data. Effectively managing, understanding, and retrieving information from this data remains a major challenge. Therefore, we propose an ontology‐based approach to integrate heterogeneous data, enable semantic queries, and support decision‐making.
Mina Abd Nikooie Pour +5 more
wiley +1 more source
SensorsThe annotation of magnetic resonance imaging (MRI) images plays an important role in deep learning-based MRI segmentation tasks. Semi-automatic annotation algorithms are helpful for improving the efficiency and reducing the difficulty of MRI image ...
Shaolong Chen, Zhiyong Zhang
doaj +1 more source
Active learning for deep object detection by fully exploiting unlabeled data
Connection Science, 2023 Object detection is a challenging task that requires a large amount of labeled data to train high-performance models. However, labeling huge amounts of data is expensive, making it difficult to train a good detector with limited labeled data.
Feixiang Tan, Guansheng Zheng
doaj +1 more source
CLASSIFICATION BASED ON SEMI-SUPERVISED LEARNING: A REVIEW
Iraqi Journal for Computers and Informatics, 2021 Semi-supervised learning is the class of machine learning that deals with the use of supervised and unsupervised learning to implement the learning process. Conceptually placed between labelled and unlabeled data.
Aska Ezadeen Mehyadin +1 more
doaj +1 more source
Advanced Engineering Materials, EarlyView.Additive manufacturing provides precise control over the placement of continuous fibres within polymer matrices, enabling customised mechanical performance in composite components. This article explores processing strategies, mechanical testing, and modelling approaches for additive manufactured continuous fibre‐reinforced composites.
Cherian Thomas, Amir Hosein Sakhaei
wiley +1 more source
Semantic Segmentation with Active Semi-Supervised Representation Learning [PDF]
, 2022 Aneesh Rangnekar +2 more
openalex +1 more source
Semi-Supervised Learning for Neural Keyphrase Generation
, 2018 We study the problem of generating keyphrases that summarize the key points for a given document. While sequence-to-sequence (seq2seq) models have achieved remarkable performance on this task (Meng et al., 2017), model training often relies on large ...
Wang, Lu, Ye, Hai
core +1 more source