Zobrazeno 1 - 10
of 29
pro vyhledávání: '"Patryk Najgebauer"'
Publikováno v:
Artificial Intelligence and Soft Computing ISBN: 9783031234798
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::37b020cd202dab187f4d3e1b7f4cb548
https://doi.org/10.1007/978-3-031-23480-4_20
https://doi.org/10.1007/978-3-031-23480-4_20
Publikováno v:
Artificial Intelligence and Soft Computing ISBN: 9783031234798
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::054736be03cce2263b0fc9f1aef57dda
https://doi.org/10.1007/978-3-031-23480-4_7
https://doi.org/10.1007/978-3-031-23480-4_7
Publikováno v:
Journal of Artificial Intelligence and Soft Computing Research. 10:113-123
Large-scale image repositories are challenging to perform queries based on the content of the images. The paper proposes a novel, nested-dictionary data structure for indexing image local features. The method transforms image local feature vectors in
Publikováno v:
Applied Soft Computing. 132:109837
Autor:
Patryk Najgebauer, Rafał Scherer
Publikováno v:
Computer Graphics Forum. 38:203-213
Publikováno v:
Computational Science – ICCS 2021 ISBN: 9783030779665
ICCS (3)
ICCS (3)
One of the outstanding benchmark architectures for point cloud processing with graph-based structures is Dynamic Graph Convolutional Neural Network (DGCNN). Though it works well for classification of nearly perfectly described digital models, it leav
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ade231a5189ef1c57979bba8d90d03ba
https://doi.org/10.1007/978-3-030-77967-2_19
https://doi.org/10.1007/978-3-030-77967-2_19
Publikováno v:
Artificial Intelligence and Soft Computing ISBN: 9783030879853
ICAISC (1)
ICAISC (1)
In this paper, we propose the Convolutional Restricted Boltzmann Machine (CRBM) as a tool for detecting concept drift in time-varying data streams. Recently, it was demonstrated that the Restricted Boltzmann Machine (RBM) can be successfully applied
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fd68cb692e3c3ae5c75ef780b058f8bd
https://doi.org/10.1007/978-3-030-87986-0_30
https://doi.org/10.1007/978-3-030-87986-0_30
Publikováno v:
Artificial Intelligence and Soft Computing ISBN: 9783030879853
ICAISC (1)
ICAISC (1)
One of the greatest challenges facing researchers of machine learning algorithms nowadays is the desire to minimize the training time of these algorithms. One of the most promising and unexplored structures of the neural network is the Restricted Bol
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::745dd92ffe959baa03cf18b6f9375fcc
https://doi.org/10.1007/978-3-030-87986-0_27
https://doi.org/10.1007/978-3-030-87986-0_27
Publikováno v:
Artificial Intelligence and Soft Computing ISBN: 9783030879853
ICAISC (1)
ICAISC (1)
The backpropagation (BP) algorithm is a worldwide used method for learning neural networks. The BP has a low computational load. Unfortunately, this method converges relatively slowly. In this paper a new approach to the backpropagation algorithm is
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0ba17bba217158113a111a975c6d00a6
https://doi.org/10.1007/978-3-030-87986-0_5
https://doi.org/10.1007/978-3-030-87986-0_5
Publikováno v:
SOCA
In this paper, we present a novel architecture for content-based image retrieval systems. Effective storing, browsing and searching collections of images is one of the most critical challenges of computer science. The design of architecture for stori