Zobrazeno 1 - 10
of 35
pro vyhledávání: '"Staerman, Guillaume"'
Physiological signal analysis often involves identifying events crucial to understanding biological dynamics. Traditional methods rely on handcrafted procedures or supervised learning, presenting challenges such as expert dependence, lack of robustne
Externí odkaz:
http://arxiv.org/abs/2406.16938
Many modern spatio-temporal data sets, in sociology, epidemiology or seismology, for example, exhibit self-exciting characteristics, triggering and clustering behaviors both at the same time, that a suitable Hawkes space-time process can accurately c
Externí odkaz:
http://arxiv.org/abs/2406.06849
Functional Isolation Forest (FIF) is a recent state-of-the-art Anomaly Detection (AD) algorithm designed for functional data. It relies on a tree partition procedure where an abnormality score is computed by projecting each curve observation on a dra
Externí odkaz:
http://arxiv.org/abs/2403.04405
Hallucinated translations pose significant threats and safety concerns when it comes to the practical deployment of machine translation systems. Previous research works have identified that detectors exhibit complementary performance different detect
Externí odkaz:
http://arxiv.org/abs/2402.13331
The landscape of available textual adversarial attacks keeps growing, posing severe threats and raising concerns regarding the deep NLP system's integrity. However, the crucial problem of defending against malicious attacks has only drawn the attenti
Externí odkaz:
http://arxiv.org/abs/2310.14001
One of the pursued objectives of deep learning is to provide tools that learn abstract representations of reality from the observation of multiple contextual situations. More precisely, one wishes to extract disentangled representations which are (i)
Externí odkaz:
http://arxiv.org/abs/2310.13990
A key feature of out-of-distribution (OOD) detection is to exploit a trained neural network by extracting statistical patterns and relationships through the multi-layer classifier to detect shifts in the expected input data distribution. Despite achi
Externí odkaz:
http://arxiv.org/abs/2306.03522
Autor:
Aghbalou, Anass, Staerman, Guillaume
Hypothesis transfer learning (HTL) contrasts domain adaptation by allowing for a previous task leverage, named the source, into a new one, the target, without requiring access to the source data. Indeed, HTL relies only on a hypothesis learnt from su
Externí odkaz:
http://arxiv.org/abs/2305.19694
Autor:
Darrin, Maxime, Staerman, Guillaume, Gomes, Eduardo Dadalto Câmara, Cheung, Jackie CK, Piantanida, Pablo, Colombo, Pierre
Out-of-distribution (OOD) detection is a rapidly growing field due to new robustness and security requirements driven by an increased number of AI-based systems. Existing OOD textual detectors often rely on an anomaly score (e.g., Mahalanobis distanc
Externí odkaz:
http://arxiv.org/abs/2302.09852
Publikováno v:
NeurIPS 2022
Deep learning methods have boosted the adoption of NLP systems in real-life applications. However, they turn out to be vulnerable to distribution shifts over time which may cause severe dysfunctions in production systems, urging practitioners to deve
Externí odkaz:
http://arxiv.org/abs/2211.13527