Zobrazeno 1 - 10
of 37 039
pro vyhledávání: '"Synthetic Datasets"'
Synthetic datasets are important for evaluating and testing machine learning models. When evaluating real-life recommender systems, high-dimensional categorical (and sparse) datasets are often considered. Unfortunately, there are not many solutions t
Externí odkaz:
http://arxiv.org/abs/2412.06809
Autor:
Hu, Jinbo, Cao, Yin, Wu, Ming, Kang, Fang, Yang, Feiran, Wang, Wenwu, Plumbley, Mark D., Yang, Jun
Sound event localization and detection (SELD) has seen substantial advancements through learning-based methods. These systems, typically trained from scratch on specific datasets, have shown considerable generalization capabilities. Recently, deep ne
Externí odkaz:
http://arxiv.org/abs/2411.06399
Autor:
Tribel, Pascal, Bontempi, Gianluca
Seismic data is often sparse and unevenly distributed due to the high costs and logistical challenges associated with deploying physical seismometers, limiting the application of Machine Learning (ML) in earthquake analysis. To address this gap, we i
Externí odkaz:
http://arxiv.org/abs/2411.12636
Synthetic data generation is gaining increasing popularity in different computer vision applications. Existing state-of-the-art face recognition models are trained using large-scale face datasets, which are crawled from the Internet and raise privacy
Externí odkaz:
http://arxiv.org/abs/2410.24015
A major limitation of prompt tuning is its dependence on large labeled training datasets. Under few-shot learning settings, prompt tuning lags far behind full-model fine-tuning, limiting its scope of application. In this paper, we leverage the powerf
Externí odkaz:
http://arxiv.org/abs/2410.10865
With the ongoing energy transition, power grids are evolving fast. They operate more and more often close to their technical limit, under more and more volatile conditions. Fast, essentially real-time computational approaches to evaluate their operat
Externí odkaz:
http://arxiv.org/abs/2410.03365
Autor:
Nombo, Leila, Charest, Anne-Sophie
Differential privacy (DP) has been accepted as a rigorous criterion for measuring the privacy protection offered by random mechanisms used to obtain statistics or, as we will study here, synthetic datasets from confidential data. Methods to generate
Externí odkaz:
http://arxiv.org/abs/2405.04769
Program similarity has become an increasingly popular area of research with various security applications such as plagiarism detection, author identification, and malware analysis. However, program similarity research faces a few unique dataset quali
Externí odkaz:
http://arxiv.org/abs/2405.03478
Autor:
Cuceu, Andrei, Herrera-Alcantar, Hiram K., Gordon, Calum, Martini, Paul, Guy, Julien, Font-Ribera, Andreu, Gonzalez-Morales, Alma X., Karim, M. Abdul, Aguilar, J., Ahlen, S., Armengaud, E., Bault, A., Brooks, D., Claybaugh, T., de la Macorra, A., Doel, P., Fanning, K., Ferraro, S., Forero-Romero, J. E., Gaztañaga, E., Gontcho, S. Gontcho A, Gutierrez, G., Honscheid, K., Howlett, C., Karaçaylı, N. G., Kirkby, D., Kremin, A., Landriau, M., Goff, J. M. Le, Guillou, L. Le, Levi, M. E., Manera, M., Meisner, A., Miquel, R., Moustakas, J., Muñoz-Gutiérrez, A., Myers, A. D., Niz, G., Palanque-Delabrouille, N., Percival, W. J., Poppett, C., Prada, F., Pérez-Ràfols, I., Ramírez-Pérez, C., Ravoux, C., Rezaie, M., Rossi, G., Sanchez, E., Schlegel, D., Schubnell, M., Seo, H., Sprayberry, D., Tan, T., Tarlé, G., Vargas-Magaña, M., Walther, M., Weaver, B. A., Zhou, R., Zou, H.
The first year of data from the Dark Energy Spectroscopic Instrument (DESI) contains the largest set of Lyman-$\alpha$ (Ly$\alpha$) forest spectra ever observed. This data, collected in the DESI Data Release 1 (DR1) sample, has been used to measure t
Externí odkaz:
http://arxiv.org/abs/2404.03004
Autor:
Räisä, Ossi, Honkela, Antti
Recent studies have highlighted the benefits of generating multiple synthetic datasets for supervised learning, from increased accuracy to more effective model selection and uncertainty estimation. These benefits have clear empirical support, but the
Externí odkaz:
http://arxiv.org/abs/2402.03985