Zobrazeno 1 - 10
of 301
pro vyhledávání: '"Grosu, Radu"'
Dynamic Vision Sensors (DVS), offer a unique advantage in control applications, due to their high temporal resolution, and asynchronous event-based data. Still, their adoption in machine learning algorithms remains limited. To address this gap, and p
Externí odkaz:
http://arxiv.org/abs/2409.18038
Autor:
Bhandary, Shrajan, Kuhn, Dejan, Babaiee, Zahra, Fechter, Tobias, Spohn, Simon K. B., Zamboglou, Constantinos, Grosu, Anca-Ligia, Grosu, Radu
Accurate segmentation of prostate tumours from PET images presents a formidable challenge in medical image analysis. Despite considerable work and improvement in delineating organs from CT and MR modalities, the existing standards do not transfer wel
Externí odkaz:
http://arxiv.org/abs/2407.10537
Autor:
Lygizou, Elpiniki Maria, Reiter, Michael, Maurer-Granofszky, Margarita, Dworzak, Michael, Grosu, Radu
Acute Leukemia is the most common hematologic malignancy in children and adolescents. A key methodology in the diagnostic evaluation of this malignancy is immunophenotyping based on Multiparameter Flow Cytometry (FCM). However, this approach is manua
Externí odkaz:
http://arxiv.org/abs/2406.18309
The automated generation of diverse and complex training scenarios has been an important ingredient in many complex learning tasks. Especially in real-world application domains, such as autonomous driving, auto-curriculum generation is considered vit
Externí odkaz:
http://arxiv.org/abs/2403.17805
We introduce liquid-resistance liquid-capacitance neural networks (LRCs), a neural-ODE model which considerably improve the generalization, accuracy, and biological plausibility of electrical equivalent circuits (EECs), liquid time-constant networks
Externí odkaz:
http://arxiv.org/abs/2403.08791
Recent advances in depthwise-separable convolutional neural networks (DS-CNNs) have led to novel architectures, that surpass the performance of classical CNNs, by a considerable scalability and accuracy margin. This paper reveals another striking pro
Externí odkaz:
http://arxiv.org/abs/2401.14469
Autor:
Lemmel, Julian, Grosu, Radu
In this paper we propose real-time recurrent reinforcement learning (RTRRL), a biologically plausible approach to solving discrete and continuous control tasks in partially-observable markov decision processes (POMDPs). RTRRL consists of three parts:
Externí odkaz:
http://arxiv.org/abs/2311.04830
Ensuring safety in dynamic multi-agent systems is challenging due to limited information about the other agents. Control Barrier Functions (CBFs) are showing promise for safety assurance but current methods make strong assumptions about other agents
Externí odkaz:
http://arxiv.org/abs/2309.10657
Robust and efficient learning remains a challenging problem in robotics, in particular with complex visual inputs. Inspired by human attention mechanism, with which we quickly process complex visual scenes and react to changes in the environment, we
Externí odkaz:
http://arxiv.org/abs/2308.15327
Autor:
Lemmel, Julian, Babaiee, Zahra, Kleinlehner, Marvin, Majic, Ivan, Neubauer, Philipp, Scholz, Johannes, Grosu, Radu, Neubauer, Sophie A.
Modern tourism in the 21st century is facing numerous challenges. Among these the rapidly growing number of tourists visiting space-limited regions like historical cities, museums and bottlenecks such as bridges is one of the biggest. In this context
Externí odkaz:
http://arxiv.org/abs/2308.14516