Results 11 to 20 of about 25,867,085 (318)
Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data [PDF]
AAAI Conference on Artificial Intelligence, 2021 Deep learning techniques for separating audio into different sound sources face several challenges. Standard architectures require training separate models for different types of audio sources.
Ke Chen +5 more
semanticscholar +1 more source
Active clustering data streams with affinity propagation
ICT Express, 2022 Most existing applications have a large number of evolving data streams. Clustering data streams is still a critical problem for these applications as the data are evolving and changes over time.
Sameh Abdulah, Ph.D. +2 more
doaj +1 more source
Incremental Feature Selection Algorithm for Dynamic Partially Labeled Hybrid Data [PDF]
Jisuanji kexue, 2022 Many real-world data sets are hybrid data consisting of symbolic,numerical and missing features.For the decision labels of hybrid data,it costs much labor and it is expensive to acquire the decision labels of all data,thus the partially labeled data is ...
YAN Zhen-chao, SHU Wen-hao, XIE Xin
doaj +1 more source
Named Entity Recognition with Small Strongly Labeled and Large Weakly Labeled Data [PDF]
Annual Meeting of the Association for Computational Linguistics, 2021 Weak supervision has shown promising results in many natural language processing tasks, such as Named Entity Recognition (NER). Existing work mainly focuses on learning deep NER models only with weak supervision, i.e., without any human annotation, and ...
Haoming Jiang +4 more
semanticscholar +1 more source
BMC Bioinformatics, 2023 Background The research of biomarker-treatment interactions is commonly investigated in randomized clinical trials (RCT) for improving medicine precision. The hierarchical interaction constraint states that an interaction should only be in a model if its
Shaima Belhechmi +4 more
doaj +1 more source
Subpath Queries on Compressed Graphs: A Survey
Algorithms, 2021 Text indexing is a classical algorithmic problem that has been studied for over four decades: given a text T, pre-process it off-line so that, later, we can quickly count and locate the occurrences of any string (the query pattern) in T in time ...
Nicola Prezza
doaj +1 more source
A Survey of Surface Defect Detection of Industrial Products Based on A Small Number of Labeled Data [PDF]
arXiv.org, 2022 The surface defect detection method based on visual perception has been widely used in industrial quality inspection. Because defect data are not easy to obtain and the annotation of a large number of defect data will waste a lot of manpower and material
Qifan Jin, L. Chen
semanticscholar +1 more source
Deep convolutional Ritz method: parametric PDE surrogates without labeled data [PDF]
Applied Mathematics and Mechanics, 2022 The parametric surrogate models for partial differential equations (PDEs) are a necessary component for many applications in computational sciences, and the convolutional neural networks (CNNs) have proven to be an excellent tool to generate these ...
J. Fuhg +4 more
semanticscholar +1 more source
FGCM: Noisy Label Learning via Fine-Grained Confidence Modeling
Applied Sciences, 2022 A small portion of mislabeled data can easily limit the performance of deep neural networks (DNNs) due to their high capacity for memorizing random labels.
Shaotian Yan +3 more
doaj +1 more source
Physics informed deep learning for computational elastodynamics without labeled data [PDF]
Journal of engineering mechanics, 2020 Numerical methods such as finite element have been flourishing in the past decades for modeling solid mechanics problems via solving governing partial differential equations (PDEs).
Chengping Rao, Hao Sun, Yang Liu
semanticscholar +1 more source