Zobrazeno 1 - 10
of 663
pro vyhledávání: '"A Mazuelas"'
For a sequence of classification tasks that arrive over time, it is common that tasks are evolving in the sense that consecutive tasks often have a higher similarity. The incremental learning of a growing sequence of tasks holds promise to enable acc
Externí odkaz:
http://arxiv.org/abs/2310.15974
High-dimensional data is common in multiple areas, such as health care and genomics, where the number of features can be tens of thousands. In such scenarios, the large number of features often leads to inefficient learning. Constraint generation met
Externí odkaz:
http://arxiv.org/abs/2306.06649
Publikováno v:
MILCOM 2021 - 2021 IEEE Military Communications Conference (MILCOM), San Diego, CA, USA, 2021, pp. 533-537
Localization systems based on ultra-wide band (UWB) measurements can have unsatisfactory performance in harsh environments due to the presence of non-line-of-sight (NLOS) errors. Learning-based methods for error mitigation have shown great performanc
Externí odkaz:
http://arxiv.org/abs/2305.18208
Publikováno v:
2021 IEEE Global Communications Conference (GLOBECOM), Madrid, Spain, 2021, pp. 1-6
Received waveforms contain rich information for both range information and environment semantics. However, its full potential is hard to exploit under multipath and non-line-of-sight conditions. This paper proposes a deep generative model (DGM) for s
Externí odkaz:
http://arxiv.org/abs/2305.18206
Publikováno v:
021 IEEE Globecom Workshops (GC Wkshps), Madrid, Spain, 2021, pp. 1-5
Radio frequency (RF)-based techniques are widely adopted for indoor localization despite the challenges in extracting sufficient information from measurements. Soft range information (SRI) offers a promising alternative for highly accurate localizati
Externí odkaz:
http://arxiv.org/abs/2305.13911
Publikováno v:
MILCOM 2021 - 2021 IEEE Military Communications Conference (MILCOM), San Diego, CA, USA, 2021, pp. 528-532
Ultra-wideband (UWB)-based techniques, while becoming mainstream approaches for high-accurate positioning, tend to be challenged by ranging bias in harsh environments. The emerging learning-based methods for error mitigation have shown great performa
Externí odkaz:
http://arxiv.org/abs/2305.13904
Publikováno v:
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapore, Singapore, 2022, pp. 2684-2688
Deep generative models (DGMs) and their conditional counterparts provide a powerful ability for general-purpose generative modeling of data distributions. However, it remains challenging for existing methods to address advanced conditional generative
Externí odkaz:
http://arxiv.org/abs/2305.13872
Supervised learning is often affected by a covariate shift in which the marginal distributions of instances (covariates $x$) of training and testing samples $\mathrm{p}_\text{tr}(x)$ and $\mathrm{p}_\text{te}(x)$ are different but the label condition
Externí odkaz:
http://arxiv.org/abs/2305.08637
Autor:
Edgar Creus‐Bachiller, Juana Fernández‐Rodríguez, Miriam Magallón‐Lorenz, Sara Ortega‐Bertran, Susana Navas‐Rutete, Cleofe Romagosa, Tulio M. Silva, Maria Pané, Anna Estival, Diana Perez Sidelnikova, Mireia Morell, Helena Mazuelas, Meritxell Carrió, Tereza Lausová, David Reuss, Bernat Gel, Alberto Villanueva, Eduard Serra, Conxi Lázaro
Publikováno v:
Molecular Oncology, Vol 18, Iss 4, Pp 895-917 (2024)
Malignant peripheral nerve sheath tumors (MPNSTs) are aggressive soft‐tissue sarcomas with a poor survival rate, presenting either sporadically or in the context of neurofibromatosis type 1 (NF1). The histological diagnosis of MPNSTs can be challen
Externí odkaz:
https://doaj.org/article/7781165f8bd2471e855029a3e508c066
The statistical characteristics of instance-label pairs often change with time in practical scenarios of supervised classification. Conventional learning techniques adapt to such concept drift accounting for a scalar rate of change by means of a care
Externí odkaz:
http://arxiv.org/abs/2205.15942