Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Marcin Kurdziel"'
Autor:
Stanisław Kaźmierczak, Zofia Juszka, Rafał Grzeszczuk, Marcin Kurdziel, Vaska Vandevska-Radunovic, Piotr Fudalej, Jacek Mańdziuk
Publikováno v:
Communications in Computer and Information Science ISBN: 9789819916474
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8ac5f5cfdc79974a2ea2cfa806212284
https://doi.org/10.1007/978-981-99-1648-1_33
https://doi.org/10.1007/978-981-99-1648-1_33
Autor:
Marcin Kurdziel, Krzysztof Boryczko
Publikováno v:
Pattern Recognition Letters. 128:306-310
In this work we propose rank densities, a novel density measure for non-metric data. Unlike typical measures employed in density clustering algorithms, rank densities are defined via ranks of patterns in k-nearest neighbor lists. Therefore they depen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e0be460523374e1a41f00e6efcea6fa9
https://doi.org/10.1016/j.patrec.2019.09.013
https://doi.org/10.1016/j.patrec.2019.09.013
Publikováno v:
Computational Science – ICCS 2021 ISBN: 9783030779634
ICCS (2)
ICCS (2)
Recent research on sparse neural networks demonstrates that densely-connected models contain sparse subnetworks that are trainable from a random initialization. Existence of these so called winning tickets suggests that we may possibly forego extensi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f5015a8f660a13ae603877ce0377f7c0
https://doi.org/10.1007/978-3-030-77964-1_11
https://doi.org/10.1007/978-3-030-77964-1_11
Autor:
Marek Powroźnik, Michał Kosowski, Piotr Wawryka, Andrzej Piechowicz, Mateusz Paciorek, Marcin Kurdziel, Michał Śledź, Adrian Kłusek, Przemysław Kalawski, Julia Plewa, Wojciech Turek, Aleksander Byrski
Publikováno v:
MoMM
Recently there has been an increasing interest in telematics solutions for vehicles. These systems provide real-time danger detection, driving style evaluation or crash detection services. The provided information can significantly increase driving s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::65774ff5f3524725830a2aac59aceede
https://doi.org/10.1145/3365921.3365924
https://doi.org/10.1145/3365921.3365924
Autor:
Piotr Iwo Wójcik, Marcin Kurdziel
Publikováno v:
Pattern Analysis and Applications. 22:1221-1231
Training deep neural networks (DNNs) on high-dimensional data with no spatial structure poses a major computational problem. It implies a network architecture with a huge input layer, which greatly increases the number of weights, often making the tr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::975d111d44a8c47b18e717cd3c85cb78
https://doi.org/10.1007/s10044-018-0697-0
https://doi.org/10.1007/s10044-018-0697-0
Publikováno v:
Neurocomputing. 202:84-90
Deep neural networks have recently shown impressive performance in several machine learning tasks. An important approach to training deep networks, useful especially when labeled data is scarce, relies on unsupervised pretraining of hidden layers fol
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fa4dc8bed8a7709c232a66d7ef68d1ca
https://doi.org/10.1016/j.neucom.2016.03.044
https://doi.org/10.1016/j.neucom.2016.03.044
Publikováno v:
Intelligent Vehicles Symposium
Nowadays, the most common way to model the driver behavior is to create, under some assumptions, a model of common patterns in driver maneuvers. These patterns are often modeled with averaged driver model. While this idea is very simple and intuitive
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::966fd35752789dce94dca095a5d62621
https://doi.org/10.1109/ivs.2018.8500715
https://doi.org/10.1109/ivs.2018.8500715
Autor:
Marcin Kurdziel, Krzysztof Boryczko
Publikováno v:
Concurrency and Computation: Practice and Experience. 25:1137-1152
SUMMARY This work presents an efficient implementation of affinity propagation (AP) on clusters of graphical processing units (GPUs). AP is a state-of-the-art method for finding exemplars in data sets described by similarity matrices. It is typically
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::41f186250d0f1497d3e0dd19736e695b
https://doi.org/10.1002/cpe.2962
https://doi.org/10.1002/cpe.2962
Autor:
Karol Grzegorczyk, Marcin Kurdziel
Publikováno v:
Rep4NLP@ACL
Recently Le & Mikolov described two log-linear models, called Paragraph Vector, that can be used to learn state-of-the-art distributed representations of documents. Inspired by this work, we present Binary Paragraph Vector models: simple neural netwo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::53595e421927fac08d8b5e55e07093ed
http://arxiv.org/abs/1611.01116
http://arxiv.org/abs/1611.01116
Publikováno v:
Parallel Processing and Applied Mathematics ISBN: 9783319321486
PPAM (1)
PPAM (1)
Deep learning has recently become a subject of vigorous research in academia and is seeing increasing use in industry. It is often considered a major advance in machine learning. However, deep learning is computationally demanding and therefore requi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2a93995cdb822a93d1689927bc2ccd11
https://doi.org/10.1007/978-3-319-32149-3_44
https://doi.org/10.1007/978-3-319-32149-3_44