Zobrazeno 1 - 10
of 9 398
pro vyhledávání: '"Akl, A. A."'
Autor:
Gabriel, Béna, Timo, Wunderlich, Mahmoud, Akl, Bernhard, Vogginger, Christian, Mayr, Hector, Andres Gonzales
Neuromorphic computing aims to replicate the brain's capabilities for energy efficient and parallel information processing, promising a solution to the increasing demand for faster and more efficient computational systems. Efficient training of neura
Externí odkaz:
http://arxiv.org/abs/2412.15021
Autor:
Andrei, Vlad C., Drăguţoiu, Alexandru P., Béna, Gabriel, Akl, Mahmoud, Li, Yin, Lohrmann, Matthias, Mönich, Ullrich J., Boche, Holger
This paper explores the potential of conversion-based neuromorphic algorithms for highly accurate and energy-efficient single-snapshot multidimensional harmonic retrieval (MHR). By casting the MHR problem as a sparse recovery problem, we devise the c
Externí odkaz:
http://arxiv.org/abs/2412.04008
Visual Question Answering (VQA) systems are known for their poor performance in out-of-distribution datasets. An issue that was addressed in previous works through ensemble learning, answer re-ranking, or artificially growing the training set. In thi
Externí odkaz:
http://arxiv.org/abs/2411.17292
Autor:
Akl, Hanna Abi
We introduce SHADOW, a fine-tuned language model trained on an intermediate task using associative deductive reasoning, and measure its performance on a knowledge base construction task using Wikidata triple completion. We evaluate SHADOW on the LM-K
Externí odkaz:
http://arxiv.org/abs/2408.14849
Autor:
Akl, Hanna Abi
We introduce semantic towers, an extrinsic knowledge representation method, and compare it to intrinsic knowledge in large language models for ontology learning. Our experiments show a trade-off between performance and semantic grounding for extrinsi
Externí odkaz:
http://arxiv.org/abs/2408.14236
Autor:
Liu, Jialian, Wang, Xiaofeng, Andrade, Cristina, Duverne, Pierre-Alexandre, Zhang, Jujia, Li, Liping, Wang, Zhenyu, Navarete, Felipe, Reguitti, Andrea, Schuldt, Stefan, Cai, Yongzhi, Filippenko, Alexei V., Yang, Yi, Brink, Thomas G., Zheng, WeiKang, Esamdin, Ali, Iskandar, Abdusamatjan, Bai, Chunhai, Liu, Jinzhong, Li, Xin, Hu, Maokai, Li, Gaici, Li, Wenxiong, Ma, Xiaoran, Yan, Shengyu, Mo, Jun, Adami, Christophe, Akl, Dalya, Antier, Sarah, Broens, Eric, Ducoin, Jean-Grégoire, Elhosseiny, Eslam, Esposito, Thomas M., Freeberg, Michael, Gokulass, Priya, Hello, Patrice, Karpov, Sergey, Márquez, Isabel, Mašek, Martin, Pyshna, Oleksandra, Rajabov, Yodgor, Saint-Gelais, Denis, Serrau, Marc, Sokoliuk, Oleksii, Takey, Ali, Tanasan, Manasanun, Turpin, Damien
We present extensive photometric and spectroscopic observations of the nearby Type Ia supernova (SN) 2023wrk at a distance of about 40 Mpc. The earliest detection of this SN can be traced back to a few hours after the explosion. Within the first few
Externí odkaz:
http://arxiv.org/abs/2407.15768
Autor:
Meho, Lokman I., Akl, Elie A.
Between 2019 and 2023, sixteen universities increased their research output by over fifteen times the global average, alongside significant changes in authorship dynamics (e.g., decreased first authorship, rise in hyperprolific authors, increased mul
Externí odkaz:
http://arxiv.org/abs/2407.18331
Autor:
Chen, Zihao, Xiao, Zhili, Akl, Mahmoud, Leugring, Johannes, Olajide, Omowuyi, Malik, Adil, Dennler, Nik, Harper, Chad, Bose, Subhankar, Gonzalez, Hector A., Eshraghian, Jason, Pignari, Riccardo, Urgese, Gianvito, Andreou, Andreas G., Shankar, Sadasivan, Mayr, Christian, Cauwenberghs, Gert, Chakrabartty, Shantanu
We introduce NeuroSA, a neuromorphic architecture specifically designed to ensure asymptotic convergence to the ground state of an Ising problem using an annealing process that is governed by the physics of quantum mechanical tunneling using Fowler-N
Externí odkaz:
http://arxiv.org/abs/2406.05224
Autor:
Akl, Hanna Abi
We present a neuro-symbolic (NeSy) workflow combining a symbolic-based learning technique with a large language model (LLM) agent to generate synthetic data for code comment classification in the C programming language. We also show how generating co
Externí odkaz:
http://arxiv.org/abs/2402.16910
Autor:
Gonzalez, Hector A., Huang, Jiaxin, Kelber, Florian, Nazeer, Khaleelulla Khan, Langer, Tim, Liu, Chen, Lohrmann, Matthias, Rostami, Amirhossein, Schöne, Mark, Vogginger, Bernhard, Wunderlich, Timo C., Yan, Yexin, Akl, Mahmoud, Mayr, Christian
The joint progress of artificial neural networks (ANNs) and domain specific hardware accelerators such as GPUs and TPUs took over many domains of machine learning research. This development is accompanied by a rapid growth of the required computation
Externí odkaz:
http://arxiv.org/abs/2401.04491