Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Petra Vidnerová"'
Autor:
Petra Vidnerová, Roman Neruda
Publikováno v:
Neural Information Processing ISBN: 9783030638351
ICONIP (3)
ICONIP (3)
In this paper, we propose a multi-objective evolutionary algorithm for automatic deep neural architecture search. The algorithm optimizes the performance of the model together with the number of network parameters. This allows exploring architectures
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7d9528e0cb0daead0a5a4fc08552e512
https://doi.org/10.1007/978-3-030-63836-8_23
https://doi.org/10.1007/978-3-030-63836-8_23
Autor:
Petra Vidnerová, Jan Kalina
Publikováno v:
Proceedings of the 21st EANN (Engineering Applications of Neural Networks) 2020 Conference ISBN: 9783030487904
EANN
EANN
Common types of artificial neural networks have been well known to suffer from the presence of outlying measurements (outliers) in the data. However, there are only a few available robust alternatives for training common form of neural networks. In t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7b5e8e58333091f108366811fe9c74e7
https://doi.org/10.1007/978-3-030-48791-1_43
https://doi.org/10.1007/978-3-030-48791-1_43
Publikováno v:
Artificial Intelligence and Soft Computing ISBN: 9783030614003
ICAISC (1)
ICAISC (1)
The choice of an architecture is crucial for the performance of the neural network, and thus automatic methods for architecture search have been proposed to provide a data-dependent solution to this problem. In this paper, we deal with an automatic n
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1d0deaf599890f75ed9971ff4284f7aa
https://doi.org/10.1007/978-3-030-61401-0_25
https://doi.org/10.1007/978-3-030-61401-0_25
Autor:
Jan Kalina, Petra Vidnerová
Publikováno v:
Proceedings of the 21st EANN (Engineering Applications of Neural Networks) 2020 Conference ISBN: 9783030487904
EANN
EANN
Metalearning is a methodology aiming at recommending the most suitable algorithm (or method) from several alternatives for a particular dataset. Its classification rule is learned over an available training database of datasets. It gradually penetrat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fff24f4aad17a6b7d29112e65f7076a2
https://doi.org/10.1007/978-3-030-48791-1_39
https://doi.org/10.1007/978-3-030-48791-1_39
Autor:
Roman Neruda, Petra Vidnerová
Publikováno v:
Neural networks : the official journal of the International Neural Network Society. 127
This paper deals with the vulnerability of machine learning models to adversarial examples and its implication for robustness and generalization properties. We propose an evolutionary algorithm that can generate adversarial examples for any machine l
Autor:
Jan Kalina, Petra Vidnerová
Publikováno v:
Artificial Intelligence and Soft Computing ISBN: 9783030209117
ICAISC (1)
ICAISC (1)
Radial basis function (RBF) neural networks represent established machine learning tool with various interesting applications to nonlinear regression modeling. However, their performance may be substantially influenced by outlying measurements (outli
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8dea7d41cea6672b2d13abe7cac6c759
https://doi.org/10.1007/978-3-030-20912-4_11
https://doi.org/10.1007/978-3-030-20912-4_11
Autor:
Roman Neruda, Petra Vidnerová
Publikováno v:
Artificial Intelligence and Soft Computing ISBN: 9783319912523
ICAISC (1)
ICAISC (1)
We propose a simple way to increase the robustness of deep neural network models to adversarial examples. The new architecture obtained by stacking deep neural network and RBF network is proposed. It is shown on experiments that such architecture is
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::edb8ca85705a722831c21a72feaf1529
https://doi.org/10.1007/978-3-319-91253-0_25
https://doi.org/10.1007/978-3-319-91253-0_25
Autor:
Roman Neruda, Petra Vidnerová
Publikováno v:
FedCSIS
Deep neural networks enjoy high interest and have become the state-of-art methods in many fields of machine learning recently. Still, there is no easy way for a choice of network architecture. However, the choice of architecture can significantly inf