Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Peter Lacko"'
Autor:
Peter Laurinec, Gabriela Grmanová, Mária Lucká, Marek Loderer, Petra Vrablecová, Viera Rozinajová, Anna Bou Ezzeddine, Peter Lacko
Publikováno v:
International Journal of Hybrid Intelligent Systems. 13:99-112
The complexity of certain problems causes that classical methods for finding exact solutions have some limitations. In this paper we propose an incremental heterogeneous ensemble model for time series prediction where biologically inspired algorithms
Publikováno v:
Remediation Journal. 26:73-86
This is the fourth in a series of papers through which the authors demonstrate how numerical transport modeling can assist the remediation design engineer in predicting the progress of enhanced reductive dechlorination remediation expected in the fie
Autor:
Michal Farkas, Peter Lacko
Publikováno v:
SemEval@NAACL-HLT
In this paper, we present our system submission for the EmoContext, the third task of the SemEval 2019 workshop. Our solution is a hierarchical recurrent neural network with ELMo embeddings and regularization through dropout and Gaussian noise. We ha
Autor:
Andrej Hucko, Peter Lacko
Publikováno v:
2018 World Symposium on Digital Intelligence for Systems and Machines (DISA).
Diacritics restoration problem is defined as correct insertion of diacritic marks into a sentence without changing the context of a particular sentence. Changing a letter in a text can cause the meaning of the word to change, and therefore the meanin
Autor:
Peter Lacko, Michal Farkas
Publikováno v:
2018 World Symposium on Digital Intelligence for Systems and Machines (DISA).
In the field of natural language processing we use distributed vector representations to capture both semantic and morphological information of a word, which is a basic unit of language that possesses meaning. Naturally, these are composed into phras
Publikováno v:
2018 World Symposium on Digital Intelligence for Systems and Machines (DISA).
Analysis of results of sport matches has always been a hot topic for both data analysts and general public. Modern methods for processing data, in combination with strong computational power of computers, allow us to predict the results of the next m
Publikováno v:
WASSA@EMNLP
In this paper, we present neural models submitted to Shared Task on Implicit Emotion Recognition, organized as part of WASSA 2018. We propose a Bi-LSTM architecture with regularization through dropout and Gaussian noise. Our models use three differen
Publikováno v:
COMPUTING AND INFORMATICS; Vol. 36 No. 1 (2017): Computing and Informatics; 55-85
The main goal of the paper is to present the method of design pattern support based on principles of model driven development: the abstraction, semantics and model transformations. More specifically, the method is based on the principle of suggestion
Autor:
Peter Lacko, Aurel Paulovic
Publikováno v:
Foundations of Computing and Decision Sciences. 38:111-122
Transactional memory is a rather novel approach to concurrency control in parallel computing, that has just recently found its way into distributed systems research. However, the research concentrates mainly on single processor solutions or cluster e
Autor:
Peter Lacko, Michal Farkas
Publikováno v:
Engineering Applications of Neural Networks ISBN: 9783319651712
EANN
EANN
The prediction of electricity consumption has become an important part of managing the smart grid. Smart grid management involves energy production (from traditional and renewable sources), transportation and measurements (smart meters). Storing larg
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d449f2ca22cdc434f281a339f8425867
https://doi.org/10.1007/978-3-319-65172-9_4
https://doi.org/10.1007/978-3-319-65172-9_4