Zobrazeno 1 - 10
of 172
pro vyhledávání: '"Bouaynaya, Nidhal"'
Continual learning focuses on learning non-stationary data distribution without forgetting previous knowledge. Rehearsal-based approaches are commonly used to combat catastrophic forgetting. However, these approaches suffer from a problem called "reh
Externí odkaz:
http://arxiv.org/abs/2405.11829
Artificial intelligence (AI) and neuroscience share a rich history, with advancements in neuroscience shaping the development of AI systems capable of human-like knowledge retention. Leveraging insights from neuroscience and existing research in adve
Externí odkaz:
http://arxiv.org/abs/2404.14588
Publikováno v:
2023 26th International Conference on Information Fusion (FUSION), 1-8, 2023
The superior performance of object detectors is often established under the condition that the test samples are in the same distribution as the training data. However, in many practical applications, out-of-distribution (OOD) instances are inevitable
Externí odkaz:
http://arxiv.org/abs/2310.19119
Deep Neural Networks (DNNs) deployed to the real world are regularly subject to out-of-distribution (OoD) data, various types of noise, and shifting conceptual objectives. This paper proposes a framework for adapting to data distribution drift modele
Externí odkaz:
http://arxiv.org/abs/2308.11801
Continual learning (CL) is an approach to address catastrophic forgetting, which refers to forgetting previously learned knowledge by neural networks when trained on new tasks or data distributions. The adversarial robustness has decomposed features
Externí odkaz:
http://arxiv.org/abs/2306.17091
Autor:
Khan, Hikmat, Bouaynaya, Nidhal Carla, Rasool, Ghulam, Travis, Tyler, Thompson, Lacey, Johnson, Charles C.
Historically, the rotorcraft community has experienced a higher fatal accident rate than other aviation segments, including commercial and general aviation. Recent advancements in artificial intelligence (AI) and the application of these technologies
Externí odkaz:
http://arxiv.org/abs/2306.17104
Autor:
Nielsen, Ian E., Ramachandran, Ravi P., Bouaynaya, Nidhal, Fathallah-Shaykh, Hassan M., Rasool, Ghulam
The expansion of explainable artificial intelligence as a field of research has generated numerous methods of visualizing and understanding the black box of a machine learning model. Attribution maps are generally used to highlight the parts of the i
Externí odkaz:
http://arxiv.org/abs/2303.08866
The quality and richness of feature maps extracted by convolution neural networks (CNNs) and vision Transformers (ViTs) directly relate to the robust model performance. In medical computer vision, these information-rich features are crucial for detec
Externí odkaz:
http://arxiv.org/abs/2302.00220
Autor:
Carannante, Giuseppina, Dera, Dimah, Bouaynaya, Nidhal C., Fathallah-Shaykh, Hassan M., Rasool, Ghulam
Deep Learning (DL) holds great promise in reshaping the healthcare industry owing to its precision, efficiency, and objectivity. However, the brittleness of DL models to noisy and out-of-distribution inputs is ailing their deployment in the clinic. M
Externí odkaz:
http://arxiv.org/abs/2111.05978
Autor:
Carannante, Giuseppina, Dera, Dimah, Rasool, Ghulam, Bouaynaya, Nidhal C., Mihaylova, Lyudmila
Learning in uncertain, noisy, or adversarial environments is a challenging task for deep neural networks (DNNs). We propose a new theoretically grounded and efficient approach for robust learning that builds upon Bayesian estimation and Variational I
Externí odkaz:
http://arxiv.org/abs/2111.05953