Results 31 to 40 of about 523,420 (188)
Online Graph Dictionary Learning
, 2021 Dictionary learning is a key tool for representation learning, that explains the data as linear combination of few basic elements. Yet, this analysis is not amenable in the context of graph learning, as graphs usually belong to different metric spaces. We fill this gap by proposing a new online Graph Dictionary Learning approach, which uses the Gromov ...
Vincent-Cuaz, Cédric +4 more
openaire +3 more sources
Efficient Approximate Online Convolutional Dictionary Learning
IEEE Transactions on Computational Imaging, 2023 Most existing convolutional dictionary learning (CDL) algorithms are based on batch learning, where the dictionary filters and the convolutional sparse representations are optimized in an alternating manner using a training dataset. When large training datasets are used, batch CDL algorithms become prohibitively memory-intensive.
Farshad G. Veshki, Sergiy A. Vorobyov
openaire +2 more sources
Lexikos, 2016 A collaboration between the Dictionary Unit for South African English (DSAE) and Stellenbosch University (SU) was initiated in 2016 to address the structure, layout and functionality of the online Dictionary of South African English on Historical ...
André Du Plessis, Tim Van Niekerk
doaj +1 more source
Bytes, Words, Texts: The Anglo-Norman Dictionary and its Text-Base
Digital Medievalist, 2012 This paper summarizes how the Anglo-Norman Dictionary project has developed from an originally paper-based and print dictionary, to a fully digital, freely available online resource, comprising not only the Dictionary itself, but a substantial text-base ...
David Trotter
doaj +1 more source
Kamusku Application as a Media in Reading Online English News
Journal of English Language Teaching Fakultas Pendidikan Bahasa dan Seni Program Studi Pendidikan Bahasa Inggris IKIP Mataram, 2023 This study aims to find out the students’ perceptions in using the application of the English Dictionary "Kamusku" as a media in reading online English news can make them feel more easier in learning vocabulary and understand the English online news well.
Ari Astutik, Yulis Setyowati
doaj +1 more source
A Novel Hyperspectral Endmember Extraction Algorithm Based on Online Robust Dictionary Learning
Remote Sensing, 2019 Due to the sparsity of hyperspectral images, the dictionary learning framework has been applied in hyperspectral endmember extraction. However, current endmember extraction methods based on dictionary learning are not robust enough in noisy environments.
Xiaorui Song, Lingda Wu
doaj +1 more source
Online group-structured dictionary learning [PDF]
CVPR 2011, 2011 We develop a dictionary learning method which is (i) online, (ii) enables overlapping group structures with (iii) non-convex sparsity-inducing regularization and (iv) handles the partially observable case. Structured sparsity and the related group norms have recently gained widespread attention in group-sparsity regularized problems in the case when ...
Zoltan Szabo +2 more
openaire +1 more source
'n Model vir 'n aanlyn GIS-vakwoordeboek
Lexikos, 2020 A Model for an Online Specialized Dictionary for GIS.As part of a MA study completed at Stellenbosch University, a model for an online specialized dictionary for GIS was developed to address three problems.
Lize-Mari Theron
doaj +1 more source
Designing a multilingual dictionary of genetic terms (English, French, German and Spanish) for the European Portal Eurogene and the International Scientific Community [PDF]
, 2014 In the framework of the DICGENETIC Project Applying Information Technologies to Designing an English-French-German-Spanish Dictionary of Genetic Terms, financed by the Regional Government of Castilla y León, the distinguished research group team ...
Cuéllar Lázaro, Carmen +2 more
core +3 more sources
Trainlets: Dictionary Learning in High Dimensions
, 2016 Sparse representations has shown to be a very powerful model for real world signals, and has enabled the development of applications with notable performance.
Elad, Michael +3 more
core +1 more source