Zobrazeno 1 - 10
of 35
pro vyhledávání: '"Marco Wiering"'
Publikováno v:
Multimodal Technologies and Interaction, Vol 3, Iss 3, p 58 (2019)
Keyphrase extraction is an important part of natural language processing (NLP) research, although little research is done in the domain of web pages. The World Wide Web contains billions of pages that are potentially interesting for various NLP tasks
Externí odkaz:
https://doaj.org/article/20bc577c158b451da22940f8dc3ccc04
Publikováno v:
NLPIR 2021: 2021 5th International Conference on Natural Language Processing and Information Retrieval (NLPIR), 30-38
STARTPAGE=30;ENDPAGE=38;TITLE=NLPIR 2021
STARTPAGE=30;ENDPAGE=38;TITLE=NLPIR 2021
Word embeddings are used as building blocks for a wide range of natural language processing and information retrieval tasks. These embeddings are usually represented as continuous vectors, requiring significant memory capacity and computationally exp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::392aaf691b2446b42e2889941731b8c5
https://doi.org/10.1145/3508230.3508235
https://doi.org/10.1145/3508230.3508235
Publikováno v:
University of Groningen
Labeling data can be an expensive task as it is usually performed manually by domain experts. This is cumbersome for deep learning, as it is dependent on large labeled datasets. Active learning (AL) is a paradigm that aims to reduce labeling effort b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::50e7614499164dbb5bc65aa779ebca7a
Publikováno v:
ArXiv. Cornell University Press
University of Groningen
University of Groningen
This paper makes one step forward towards characterizing a new family of \textit{model-free} Deep Reinforcement Learning (DRL) algorithms. The aim of these algorithms is to jointly learn an approximation of the state-value function ($V$), alongside a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c76dae7d0a3a4949aa8181cfb768d24c
http://arxiv.org/abs/1909.01779
http://arxiv.org/abs/1909.01779
Autor:
Marco Wiering
Publikováno v:
Communications in Computer and Information Science ISBN: 9783030319779
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bbbaf767f1f2721628ed2b95a5ceec1f
https://doi.org/10.1007/978-3-030-31978-6
https://doi.org/10.1007/978-3-030-31978-6
Publikováno v:
ArXiv. Cornell University Press
Scopus-Elsevier
University of Groningen
Scopus-Elsevier
University of Groningen
We introduce a novel Deep Reinforcement Learning (DRL) algorithm called Deep Quality-Value (DQV) Learning. DQV uses temporal-difference learning to train a Value neural network and uses this network for training a second Quality-value network that le
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::81c64e99f2a60f866492980a47400aa9
https://research.rug.nl/en/publications/c8f24bfd-29d3-4718-a074-93c2ecde7be6
https://research.rug.nl/en/publications/c8f24bfd-29d3-4718-a074-93c2ecde7be6
Publikováno v:
ArXiv. Cornell University Press
University of Groningen
University of Groningen
In this paper, a new offline actor-critic learning algorithm is introduced: Sampled Policy Gradient (SPG). SPG samples in the action space to calculate an approximated policy gradient by using the critic to evaluate the samples. This sampling allows
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::48e762ba8cf82344d42e62932113380d
https://research.rug.nl/en/publications/769cda31-8ddf-443c-b13e-89006b8d3f91
https://research.rug.nl/en/publications/769cda31-8ddf-443c-b13e-89006b8d3f91
Autor:
Mathijs Pieters, Marco Wiering
Publikováno v:
University of Groningen
Generative adversarial networks (GANs) have demonstrated to be successful at generating realistic real-world images. In this paper we compare various GAN techniques, both supervised and unsupervised. The effects on training stability of different obj
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6582a025335c636d73963f6d12ffa6a0
http://arxiv.org/abs/1803.09093
http://arxiv.org/abs/1803.09093
Publikováno v:
Communications in Computer and Information Science ISBN: 9783319768915
This book contains a selection of the best papers of the 29th Benelux Conference on Artificial Intelligence, BNAIC 2017, held in Groningen, The Netherlands, in November 2017. The 11 full papers presented in this volume were carefully reviewed and sel
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9fb292cf2fa5d78c313fe21985404281
https://doi.org/10.1007/978-3-319-76892-2
https://doi.org/10.1007/978-3-319-76892-2
Autor:
Bart Verheij, Marco Wiering
This book contains a selection of the best papers of the 29th Benelux Conference on Artificial Intelligence, BNAIC 2017, held in Groningen, The Netherlands, in November 2017. The 11 full papers presented in this volume were carefully reviewed and se