Zobrazeno 1 - 10
of 13
pro vyhledávání: '"FERRO, MANUEL VILARES"'
Publikováno v:
Journal of Computer and System Sciences, 129 (2020) , pp 39-61. ISSN 1090-2724. Elsevier
Non-active adaptive sampling is a way of building machine learning models from a training data base which are supposed to dynamically and automatically derive guaranteed sample size. In this context and regardless of the strategy used in both schedul
Externí odkaz:
http://arxiv.org/abs/2402.02522
Publikováno v:
Computer Speech & Language, 60, 101020 (2020), pp 1-18. ISSN 0885-2308. Elsevier
We introduce an adaptive scheduling for adaptive sampling as a novel way of machine learning in the construction of part-of-speech taggers. The goal is to speed up the training on large data sets, without significant loss of performance with regard t
Externí odkaz:
http://arxiv.org/abs/2402.02516
Publikováno v:
Computer Speech & Language, 41, pp 1-28 (2017). ISSN 0885-2308. Elsevier
An algorithm to estimate the evolution of learning curves on the whole of a training data base, based on the results obtained from a portion and using a functional strategy, is introduced. We approximate iteratively the sought value at the desired ti
Externí odkaz:
http://arxiv.org/abs/2402.02515
Autor:
Ferro, Manuel Vilares, Mosquera, Yerai Doval, Pena, Francisco J. Ribadas, Bilbao, Victor M. Darriba
Publikováno v:
Neural Networks, 159 (2023), pp 109-124. ISSN 1879-2782. Elsevier
In order to minimize the generalization error in neural networks, a novel technique to identify overfitting phenomena when training the learner is formally introduced. This enables support of a reliable and trustworthy early stopping condition, thus
Externí odkaz:
http://arxiv.org/abs/2402.02513
Autor:
Ferro, Manuel Vilares, Bilbao, Víctor M. Darriba, Ribadas-Pena, Francisco J., Gil, Jorge Graña
Publikováno v:
Mathematics 2022, 10(19), 3526
The recent trend towards the application of deep structured techniques has revealed the limits of huge models in natural language processing. This has reawakened the interest in traditional machine learning algorithms, which have proved still to be c
Externí odkaz:
http://arxiv.org/abs/2402.02449
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
Proceeding of the 2nd ACM Workshop: Improving Non English Web Searching; 10/30/2008, p39-46, 8p
Publikováno v:
Computational Linguistics & Intelligent Text Processing (9783540322054); 2006, p575-585, 11p
Publikováno v:
2015 IEEE 15th International Conference on Advanced Learning Technologies; 2015, p407-408, 2p