Zobrazeno 1 - 10
of 106
pro vyhledávání: '"Ditzler, Gregory"'
Autor:
Li, Huayu, Ditzler, Gregory
Continual learning algorithms are typically exposed to untrusted sources that contain training data inserted by adversaries and bad actors. An adversary can insert a small number of poisoned samples, such as mislabeled samples from previously learned
Externí odkaz:
http://arxiv.org/abs/2311.10919
Knowledge distillation constitutes a potent methodology for condensing substantial neural networks into more compact and efficient counterparts. Within this context, softmax regression representation learning serves as a widely embraced approach, lev
Externí odkaz:
http://arxiv.org/abs/2304.11004
Autor:
Hess, Samuel, Ditzler, Gregory
Few-shot learning is a rapidly evolving area of research in machine learning where the goal is to classify unlabeled data with only one or "a few" labeled exemplary samples. Neural networks are typically trained to minimize a distance metric between
Externí odkaz:
http://arxiv.org/abs/2211.14668
Robust classification is essential in tasks like autonomous vehicle sign recognition, where the downsides of misclassification can be grave. Adversarial attacks threaten the robustness of neural network classifiers, causing them to consistently and c
Externí odkaz:
http://arxiv.org/abs/2208.09285
BACKGROUND: Some of the current software tools for comparative metagenomics provide ecologists with the ability to investigate and explore bacterial communities using α- & β-diversity. Feature subset selection - a sub-field of machine learning - ca
Externí odkaz:
http://hdl.handle.net/10150/610268
http://arizona.openrepository.com/arizona/handle/10150/610268
http://arizona.openrepository.com/arizona/handle/10150/610268
Objective: Electrocardiogram (ECG) signals commonly suffer noise interference, such as baseline wander. High-quality and high-fidelity reconstruction of the ECG signals is of great significance to diagnosing cardiovascular diseases. Therefore, this p
Externí odkaz:
http://arxiv.org/abs/2208.00542
Publikováno v:
In Neural Networks May 2024 173
Autor:
Hess, Samuel, Ditzler, Gregory
Unexplainable black-box models create scenarios where anomalies cause deleterious responses, thus creating unacceptable risks. These risks have motivated the field of eXplainable Artificial Intelligence (XAI) to improve trust by evaluating local inte
Externí odkaz:
http://arxiv.org/abs/2110.11597
Modulation Classification (MC) refers to the problem of classifying the modulation class of a wireless signal. In the wireless communications pipeline, MC is the first operation performed on the received signal and is critical for reliable decoding.
Externí odkaz:
http://arxiv.org/abs/2008.06785
Self-supervised monocular depth estimation methods generally suffer the occlusion fading issue due to the lack of supervision by the per pixel ground truth. Although a post-processing method was proposed by Godard et. al. to reduce the occlusion fadi
Externí odkaz:
http://arxiv.org/abs/1911.11705