Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Matsubara, Yoshitomo"'
Autor:
Lalande, Florian, Matsubara, Yoshitomo, Chiba, Naoya, Taniai, Tatsunori, Igarashi, Ryo, Ushiku, Yoshitaka
Symbolic Regression (SR) searches for mathematical expressions which best describe numerical datasets. This allows to circumvent interpretation issues inherent to artificial neural networks, but SR algorithms are often computationally expensive. This
Externí odkaz:
http://arxiv.org/abs/2312.04070
Autor:
Matsubara, Yoshitomo
Reproducibility in scientific work has been becoming increasingly important in research communities such as machine learning, natural language processing, and computer vision communities due to the rapid development of the research domains supported
Externí odkaz:
http://arxiv.org/abs/2310.17644
Modern IEEE 802.11 (Wi-Fi) networks extensively rely on multiple-input multiple-output (MIMO) to significantly improve throughput. To correctly beamform MIMO transmissions, the access point needs to frequently acquire a beamforming matrix (BM) from e
Externí odkaz:
http://arxiv.org/abs/2310.08656
While impressive performance has been achieved on the task of Answer Sentence Selection (AS2) for English, the same does not hold for languages that lack large labeled datasets. In this work, we propose Cross-Lingual Knowledge Distillation (CLKD) fro
Externí odkaz:
http://arxiv.org/abs/2305.16302
This paper revisits datasets and evaluation criteria for Symbolic Regression (SR), specifically focused on its potential for scientific discovery. Focused on a set of formulas used in the existing datasets based on Feynman Lectures on Physics, we rec
Externí odkaz:
http://arxiv.org/abs/2206.10540
With the increasing demand for deep learning models on mobile devices, splitting neural network computation between the device and a more powerful edge server has become an attractive solution. However, existing split computing approaches often under
Externí odkaz:
http://arxiv.org/abs/2203.08875
Publikováno v:
Findings of the Association for Computational Linguistics: EMNLP 2022
Large transformer models can highly improve Answer Sentence Selection (AS2) tasks, but their high computational costs prevent their use in many real-world applications. In this paper, we explore the following research question: How can we make the AS
Externí odkaz:
http://arxiv.org/abs/2201.05767
Autor:
Matsubara, Yoshitomo, Callegaro, Davide, Singh, Sameer, Levorato, Marco, Restuccia, Francesco
Publikováno v:
2022 IEEE 23rd International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM)
Although mission-critical applications require the use of deep neural networks (DNNs), their continuous execution at mobile devices results in a significant increase in energy consumption. While edge offloading can decrease energy consumption, errati
Externí odkaz:
http://arxiv.org/abs/2201.02693
Publikováno v:
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2022
There has been much interest in deploying deep learning algorithms on low-powered devices, including smartphones, drones, and medical sensors. However, full-scale deep neural networks are often too resource-intensive in terms of energy and storage. A
Externí odkaz:
http://arxiv.org/abs/2108.11898
Mobile devices such as smartphones and autonomous vehicles increasingly rely on deep neural networks (DNNs) to execute complex inference tasks such as image classification and speech recognition, among others. However, continuously executing the enti
Externí odkaz:
http://arxiv.org/abs/2103.04505