Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Petra Vidnerová"'
Autor:
Roman Neruda, Petra Vidnerová
Publikováno v:
Adaptive and Natural Computing Algorithms ISBN: 9783642202810
ICANNGA (1)
ICANNGA (1)
In this paper we propose a novel evolutionary algorithm for regularization networks. The main drawback of regularization networks in practical applications is the presence of meta-parameters, including the type and parameters of kernel functions Our
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9947a92fd2b2bb1fba8da2730ba2856a
https://doi.org/10.1007/978-3-642-20282-7_19
https://doi.org/10.1007/978-3-642-20282-7_19
Autor:
Roman Neruda, Petra Vidnerová
Publikováno v:
Advances in Neural Networks – ISNN 2011 ISBN: 9783642211041
ISNN (1)
ISNN (1)
This paper deals with learning possibilities of regularization networks with product kernel units. Approximation problems formulated as regularized minimization problems with kernel-based stabilizers lead to solutions of the shape of linear combinati
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::584cc830f0538fba59dcfbca742ede9c
https://doi.org/10.1007/978-3-642-21105-8_62
https://doi.org/10.1007/978-3-642-21105-8_62
Autor:
Roman Neruda, Petra Vidnerová
Publikováno v:
Artifical Intelligence and Soft Computing ISBN: 9783642132315
ICAISC (2)
ICAISC (2)
Regularization theory presents a sound framework to solving supervised learning problems. However, the regularization networks have a large size corresponding to the size of training data. In this work we study a relationship between network complexi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2a60a8443a9d11b5a0b276107a642fa5
https://doi.org/10.1007/978-3-642-13232-2_15
https://doi.org/10.1007/978-3-642-13232-2_15
Autor:
Roman Neruda, Petra Vidnerová
Publikováno v:
Advances in Neural Networks-ISNN 2010 ISBN: 9783642132773
ISNN (1)
ISNN (1)
In this work we propose two hybrid algorithms combining evolutionary search with optimization algorithms One algorithm memetically combines global evolution with gradient descent local search, while the other is a two-step procedure combining linear
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e5fd6aad83e846753c09fabd1ba5c5c6
https://doi.org/10.1007/978-3-642-13278-0_68
https://doi.org/10.1007/978-3-642-13278-0_68
Autor:
Roman Neruda, Petra Vidnerová
Publikováno v:
Advances in Information Technology ISBN: 9783642166983
IAIT
IAIT
Regularization networks are one of the important methods for supervised learning. They benefit from very good theoretical background, though their drawback is the presence of metaparameters. The metaparameters are typically supposed to be given by an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::be9ed1bc4828e1abd07fe7b001d3ebae
https://doi.org/10.1007/978-3-642-16699-0_21
https://doi.org/10.1007/978-3-642-16699-0_21
Publikováno v:
Artificial Neural Networks-ICANN 2008 ISBN: 9783540875352
ICANN (1)
ICANN (1)
An emergence of intelligent behavior within a simple robotic agent is studied in this paper. Two control mechanisms for an agent are considered -- a radial basis function neural network trained by evolutionary algorithm, and a traditional reinforceme
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::77255b76d98b2025c7c8dc73a25961b7
https://doi.org/10.1007/978-3-540-87536-9_74
https://doi.org/10.1007/978-3-540-87536-9_74
Autor:
Petra Vidnerová, Roman Neruda
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783540877318
ISNN (1)
ISNN (1)
Regularization theory presents a sound framework to solving supervised learning problems. However, there is a gap between the theoretical results and practical suitability of regularization networks (RN). Radial basis function networks (RBF) can be s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c631ab6c015615bf4645658756a00a53
https://doi.org/10.1007/978-3-540-87732-5_61
https://doi.org/10.1007/978-3-540-87732-5_61
Publikováno v:
Advanced Intelligent Computing Theories and Applications. With Aspects of Artificial Intelligence ISBN: 9783540859833
ICIC (2)
ICIC (2)
We study behavioural patterns learned by a robotic agent by means of two different control and adaptive approaches -- a radial basis function neural network trained by evolutionary algorithm, and a traditional reinforcement Q-learning algorithm. In b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ee87fe674b71c5862f453d4d628deda0
https://doi.org/10.1007/978-3-540-85984-0_35
https://doi.org/10.1007/978-3-540-85984-0_35