Zobrazeno 1 - 10
of 2 803
pro vyhledávání: '"[INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE]"'
Publikováno v:
Journal of Data Mining and Digital Humanities, Vol 2023, Iss Dataset (2023)
Machine learning begins with machine teaching: in the following paper, we present the data that we have prepared to kick-start the training of reliable OCR models for 17th century prints written in French. The construction of a representative corpus
Externí odkaz:
https://doaj.org/article/32400b495f33443e927b9457f1707236
Publikováno v:
Journal of the Korean Statistical Society. 52:154-184
The determination of the number of mixture components (the order) of a finite mixture model has been an enduring problem in statistical inference. We prove that the closed testing principle leads to a sequential testing procedure (STP) that allows fo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3d7396cb4d1f4fc74ffb1da989ce7c0b
https://doi.org/10.1007/s42952-022-00195-z
https://doi.org/10.1007/s42952-022-00195-z
Autor:
Flasseur, Olivier, Bodrito, Théo, Mairal, Julien, Ponce, Jean, Langlois, Maud, Lagrange, Anne-Marie
Publikováno v:
EUSIPCO 2023-European Signal Processing Conference
EUSIPCO 2023-European Signal Processing Conference, Sep 2023, Helsinki, Finland. pp.1-5
EUSIPCO 2023-European Signal Processing Conference, Sep 2023, Helsinki, Finland. pp.1-5
Exoplanet detection by direct imaging is a difficult task: the faint signals from the objects of interest are buried under a spatially structured nuisance component induced by the host star. The exoplanet signals can only be identified when combining
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::502581512a9224d5d4053f30122aafa4
https://hal.science/hal-04136362/file/deep_paco_asdi_eusipco_reviewed_2023.pdf
https://hal.science/hal-04136362/file/deep_paco_asdi_eusipco_reviewed_2023.pdf
Publikováno v:
Text, Speech and Dialogue 2023-Interspeech Satellite
Text, Speech and Dialogue 2023-Interspeech Satellite, Faculty of Applied Sciences University of West Bohemia Plzeň (Pilsen); NTIS P2 Research Center University of West Bohemia Plzeň (Pilsen); Faculty of Informatics Masaryk University Brno, Sep 2023, Plzeň (Pilsen), Czech Republic
Text, Speech and Dialogue 2023-Interspeech Satellite, Faculty of Applied Sciences University of West Bohemia Plzeň (Pilsen); NTIS P2 Research Center University of West Bohemia Plzeň (Pilsen); Faculty of Informatics Masaryk University Brno, Sep 2023, Plzeň (Pilsen), Czech Republic
International audience; Conventionally, Automatic Speech Recognition (ASR) systems are evaluated on their ability to correctly recognize each word contained in a speech signal. In this context, the word error rate (WER) metric is the reference for ev
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______165::2ad4ed4a6aee048afcb6ad077a8fea58
https://hal.science/hal-04125590/file/TSD_2023___HATS.pdf
https://hal.science/hal-04125590/file/TSD_2023___HATS.pdf
Publikováno v:
IEEE Transactions on Evolutionary Computation
IEEE Transactions on Evolutionary Computation, 2022, 26 (6), pp.1293--1305. ⟨10.1109/TEVC.2022.3210897⟩
IEEE Transactions on Evolutionary Computation, 2022, 26 (6), pp.1293--1305. ⟨10.1109/TEVC.2022.3210897⟩
open access; International audience; We present concepts and recipes for the anytime performance assessment when benchmarking optimization algorithms in a blackbox scenario. We consider runtime-oftentimes measured in number of blackbox evaluations ne
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c492100fdf81dadf5d56be067075205d
https://doi.org/10.1109/tevc.2022.3210897
https://doi.org/10.1109/tevc.2022.3210897
Publikováno v:
GECCO 2023-Genetic and Evolutionary Computation Conference
GECCO 2023-Genetic and Evolutionary Computation Conference, GECCO, Jul 2023, Lisbon, Portugal. ⟨10.1145/3583131.3590492⟩
Genetic and Evolutionary Computation Conference (GECCO ’23)
Genetic and Evolutionary Computation Conference (GECCO ’23), GECCO, Jul 2023, Lisbon, Portugal. ⟨10.1145/3583131.3590492⟩
GECCO 2023-Genetic and Evolutionary Computation Conference, GECCO, Jul 2023, Lisbon, Portugal. ⟨10.1145/3583131.3590492⟩
Genetic and Evolutionary Computation Conference (GECCO ’23)
Genetic and Evolutionary Computation Conference (GECCO ’23), GECCO, Jul 2023, Lisbon, Portugal. ⟨10.1145/3583131.3590492⟩
International audience; We present a surrogate-assisted multiobjective optimization algorithm. The aggregation of the objectives relies on the Uncrowded Hypervolume Improvement (UHVI) which is partly replaced by a linear-quadratic surrogate that is i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::468a649f34acfc0b4accfea5c412b5a2
https://hal.science/hal-04078483/file/gharafi2023multiobjective.pdf
https://hal.science/hal-04078483/file/gharafi2023multiobjective.pdf
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, pp.1-13. ⟨10.1109/TPAMI.2023.3291663⟩
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, pp.1-13. ⟨10.1109/TPAMI.2023.3291663⟩
International audience; Deep learning architectures, albeit successful in most computer vision tasks, were designed for data with an underlying Euclidean structure, which is not usually fulfilled since pre-processed data may lie on a non-linear space
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______165::2d16bc9de0a7f9866d13e4607c66578a
https://hal.science/hal-04155915
https://hal.science/hal-04155915
Publikováno v:
IEEE Transactions on Cybernetics
IEEE Transactions on Cybernetics, 2023, 53 (7), pp.4521--4530. ⟨10.1109/TCYB.2022.3203795⟩
IEEE Transactions on Cybernetics, 2023, 53 (7), pp.4521--4530. ⟨10.1109/TCYB.2022.3203795⟩
International audience; In this article, a novel integral reinforcement learning (RL)-based nonfragile output feedback tracking control algorithm is proposed for uncertain Markov jump nonlinear systems presented by the Takagi–Sugeno fuzzy model. Th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fd9183847d2014a7843b868373cc2b3d
https://hal.science/hal-03825983
https://hal.science/hal-03825983
Understanding the geometric properties of gradient descent dynamics is a key ingredient in deciphering the recent success of very large machine learning models. A striking observation is that trained over-parameterized models retain some properties o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0fb87a6cfe8cdb7ec6865a299255d44d
http://arxiv.org/abs/2307.00144
http://arxiv.org/abs/2307.00144
International audience; We explore different strategies to integrate prior domain knowledge into the design of a deep neural network (DNN). We focus on graph neural networks (GNN), with a use case of estimating the potential energy of chemical system
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c1fb22b5ee72d0394b71a64ed4dc8493
https://hal.science/hal-04142152/document
https://hal.science/hal-04142152/document