Zobrazeno 1 - 10
of 42
pro vyhledávání: '"Anton Akusok"'
Publikováno v:
IEEE Access, Vol 3, Pp 1011-1025 (2015)
This paper presents a complete approach to a successful utilization of a high-performance extreme learning machines (ELMs) Toolbox for Big Data. It summarizes recent advantages in algorithmic performance; gives a fresh view on the ELM solution in rel
Externí odkaz:
https://doaj.org/article/87626bdf05c44e80bd06a4aa52507db7
Publikováno v:
Proceedings of ELM 2021 ISBN: 9783031216770
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::159e7899e60b119ec5ae4cfc9ac2c250
https://doi.org/10.1007/978-3-031-21678-7_4
https://doi.org/10.1007/978-3-031-21678-7_4
Publikováno v:
Proceedings of ELM 2021 ISBN: 9783031216770
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e1458325313a111fa7b8351612b93e32
https://doi.org/10.1007/978-3-031-21678-7_12
https://doi.org/10.1007/978-3-031-21678-7_12
Publikováno v:
PETRA
Detection of fake signatures is a hard task. In this paper, we present a novel method for detecting trained forgeries using features extracted from sliding windows with different overlaps on a public available dataset of static images of signatures.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7f47f1c75fbe9f02a8dff07efe367c74
https://doi.org/10.1145/3453892.3454003
https://doi.org/10.1145/3453892.3454003
Publikováno v:
Proceedings of ELM2019 ISBN: 9783030589882
This paper presents a novel library for Extreme Learning Machines (ELM) called Scikit-ELM (https://github.com/akusok/scikit-elm, https://scikit-elm.readthedocs.io). Usability and flexibility of the approach are the main focus points in this work, ach
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9909cac0bd49acafa70c113ffe683589
https://doi.org/10.1007/978-3-030-58989-9_8
https://doi.org/10.1007/978-3-030-58989-9_8
Publikováno v:
Proceedings of ELM2019 ISBN: 9783030589882
This paper proposes a block solution method for the Extreme Learning Machine. It combines the speed of a direct non-iterative solver with minimal memory requirements. The method is suitable for edge computing scenarios running on a mobile device with
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::63c31c968d84865ca516823a7f363668
https://doi.org/10.1007/978-3-030-58989-9_9
https://doi.org/10.1007/978-3-030-58989-9_9
Publikováno v:
Proceedings of ELM2019 ISBN: 9783030589882
In this paper, we present a fast and accurate method for the classification of web content. Our algorithm uses the visual information of the main homepage saved in an image format by means of a full body snapshot. Sliding windows of different sizes a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::df1d45a15952bdb8cfb963d719dc7ff0
https://doi.org/10.1007/978-3-030-58989-9_5
https://doi.org/10.1007/978-3-030-58989-9_5
Publikováno v:
Proceedings of ELM2019 ISBN: 9783030589882
In this paper, we present a novel approach to the verification of users through their own handwritten static signatures using the extreme learning machine (ELM) methodology. Our work uses the features extracted from the last fully connected layer of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1a365248d5dfe5dbeabc53bb9a2fd012
https://doi.org/10.1007/978-3-030-58989-9_4
https://doi.org/10.1007/978-3-030-58989-9_4
Publikováno v:
Proceedings of ELM2019 ISBN: 9783030589882
We present a process for validating and improving annotations made by untrained humans using a two-step machine learning algorithm. The initial validation algorithm is trained on a high quality annotated subset of the data that the untrained humans a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::38e89afe43bc31385b226a2ff4f8c4c9
https://doi.org/10.1007/978-3-030-58989-9_10
https://doi.org/10.1007/978-3-030-58989-9_10
Publikováno v:
Cognitive Computation. 10:464-477
The current paper presents an improvement of the Extreme Learning Machines for VISualization (ELMVIS+) nonlinear dimensionality reduction method. In this improved method, called ELMVIS+R, it is proposed to apply the originally unsupervised ELMVIS+ me
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::58e2f7b439c3b1c566547dfbd4bbb7ce
https://doi.org/10.1007/s12559-017-9537-6
https://doi.org/10.1007/s12559-017-9537-6