Zobrazeno 1 - 10
of 1 138
pro vyhledávání: '"Darriba, A"'
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
Publikováno v:
Mathematics 2022, 10(16), 2867
In this paper, we introduce a multi-label lazy learning approach to deal with automatic semantic indexing in large document collections in the presence of complex and structured label vocabularies with high inter-label correlation. The proposed metho
Externí odkaz:
http://arxiv.org/abs/2402.01963
Autor:
Dhiman, Vinit, Gupta, Alok C., Bachev, Rumen, Wiita, Paul J., Cellone, Sergio A., Strigachev, A., Gaur, Haritma, Darriba, A., Bisen, D. P., Locatelli, G., Mammana, L. A., Semkov, E.
We report the first extensive optical flux and spectral variability study of the TeV blazar TXS 0506+056 on intra-night to long-term timescales using BVRI data collected over 220 nights between January 21, 2017 to April 9, 2022 using 8 optical ground
Externí odkaz:
http://arxiv.org/abs/2311.02352
Autor:
Ríos-Monje, Carlos, Parra-Royón, Manuel, Moldón, Javier, Sánchez-Expósito, Susana, Garrido, Julián, Darriba, Laura, Mendoza, MAngeles, Sánchez, Jesús, Verdes-Montenegro, Lourdes, Salgado, Jesús
Function-as-a-Service (FaaS) is a type of serverless computing that allows developers to write and deploy code as individual functions, which can be triggered by specific events or requests. FaaS platforms automatically manage the underlying infrastr
Externí odkaz:
http://arxiv.org/abs/2306.09728
Autor:
Hartley, P., Bonaldi, A., Braun, R., Aditya, J. N. H. S., Aicardi, S., Alegre, L., Chakraborty, A., Chen, X., Choudhuri, S., Clarke, A. O., Coles, J., Collinson, J. S., Cornu, D., Darriba, L., Veneri, M. Delli, Forbrich, J., Fraga, B., Galan, A., Garrido, J., Gubanov, F., Håkansson, H., Hardcastle, M. J., Heneka, C., Herranz, D., Hess, K. M., Jagannath, M., Jaiswal, S., Jurek, R. J., Korber, D., Kitaeff, S., Kleiner, D., Lao, B., Lu, X., Mazumder, A., Moldón, J., Mondal, R., Ni, S., Önnheim, M., Parra, M., Patra, N., Peel, A., Salomé, P., Sánchez-Expósito, S., Sargent, M., Semelin, B., Serra, P., Shaw, A. K., Shen, A. X., Sjöberg, A., Smith, L., Soroka, A., Stolyarov, V., Tolley, E., Toribio, M. C., van der Hulst, J. M., Sadr, A. Vafaei, Verdes-Montenegro, L., Westmeier, T., Yu, K., Yu, L., Zhang, L., Zhang, X., Zhang, Y., Alberdi, A., Ashdown, M., Bom, C. R., Brüggen, M., Cannon, J., Chen, R., Combes, F., Conway, J., Courbin, F., Ding, J., Fourestey, G., Freundlich, J., Gao, L., Gheller, C., Guo, Q., Gustavsson, E., Jirstrand, M., Jones, M. G., Józsa, G., Kamphuis, P., Kneib, J. -P., Lindqvist, M., Liu, B., Liu, Y., Mao, Y., Marchal, A., Márquez, I., Meshcheryakov, A., Olberg, M., Oozeer, N., Pandey-Pommier, M., Pei, W., Peng, B., Sabater, J., Sorgho, A., Starck, J. L., Tasse, C., Wang, A., Wang, Y., Xi, H., Yang, X., Zhang, H., Zhang, J., Zhao, M., Zuo, S.
The Square Kilometre Array Observatory (SKAO) will explore the radio sky to new depths in order to conduct transformational science. SKAO data products made available to astronomers will be correspondingly large and complex, requiring the application
Externí odkaz:
http://arxiv.org/abs/2303.07943
Autor:
Javier Gómez Darriba
Publikováno v:
Anuario de Estudios Americanos, Vol 81, Iss 1 (2024)
Externí odkaz:
https://doaj.org/article/3d9ac88b442b412e9d6a357adff3ddaa
