Zobrazeno 1 - 10
of 927
pro vyhledávání: '"Hammer, Barbara"'
In recent studies, line search methods have been demonstrated to significantly enhance the performance of conventional stochastic gradient descent techniques across various datasets and architectures, while making an otherwise critical choice of lear
Externí odkaz:
http://arxiv.org/abs/2407.20650
Autor:
Artelt, André, Hammer, Barbara
EXplainable AI (XAI) constitutes a popular method to analyze the reasoning of AI systems by explaining their decision-making, e.g. providing a counterfactual explanation of how to achieve recourse. However, in cases such as unexpected explanations, t
Externí odkaz:
http://arxiv.org/abs/2406.03012
Autor:
Artelt, André, Kyriakou, Marios S., Vrachimis, Stelios G., Eliades, Demetrios G., Hammer, Barbara, Polycarpou, Marios M.
Drinking water is a vital resource for humanity, and thus, Water Distribution Networks (WDNs) are considered critical infrastructures in modern societies. The operation of WDNs is subject to diverse challenges such as water leakages and contamination
Externí odkaz:
http://arxiv.org/abs/2406.02078
Autor:
Fumagalli, Fabian, Muschalik, Maximilian, Kolpaczki, Patrick, Hüllermeier, Eyke, Hammer, Barbara
The Shapley value (SV) is a prevalent approach of allocating credit to machine learning (ML) entities to understand black box ML models. Enriching such interpretations with higher-order interactions is inevitable for complex systems, where the Shaple
Externí odkaz:
http://arxiv.org/abs/2405.10852
Autor:
Internò, Christian, Raponi, Elena, van Stein, Niki, Bäck, Thomas, Olhofer, Markus, Jin, Yaochu, Hammer, Barbara
Federated learning (FL) represents a pivotal shift in machine learning (ML) as it enables collaborative training of local ML models coordinated by a central aggregator, all without the need to exchange local data. However, its application on edge dev
Externí odkaz:
http://arxiv.org/abs/2405.10271
Several related works have introduced Koopman-based Machine Learning architectures as a surrogate model for dynamical systems. These architectures aim to learn non-linear measurements (also known as observables) of the system's state that evolve by a
Externí odkaz:
http://arxiv.org/abs/2405.06425
In the realm of fashion object detection and segmentation for online shopping images, existing state-of-the-art fashion parsing models encounter limitations, particularly when exposed to non-model-worn apparel and close-up shots. To address these fai
Externí odkaz:
http://arxiv.org/abs/2404.08582
Pretraining language models on large text corpora is a common practice in natural language processing. Fine-tuning of these models is then performed to achieve the best results on a variety of tasks. In this paper, we investigate the problem of catas
Externí odkaz:
http://arxiv.org/abs/2404.01317
Water distribution systems (WDS) are an integral part of critical infrastructure which is pivotal to urban development. As 70% of the world's population will likely live in urban environments in 2050, efficient simulation and planning tools for WDS p
Externí odkaz:
http://arxiv.org/abs/2403.18570
Over the last years, various sentence embedders have been an integral part in the success of current machine learning approaches to Natural Language Processing (NLP). Unfortunately, multiple sources have shown that the bias, inherent in the datasets
Externí odkaz:
http://arxiv.org/abs/2403.18555