Výsledky vyhledávání - "MUNAKATA, Kazuki"

Report

An Exploratory Study of AI System Risk Assessment from the Lens of Data Distribution and Uncertainty

Autor: Wang, Zhijie, Huang, Yuheng, Ma, Lei, Yokoyama, Haruki, Tokumoto, Susumu, Munakata, Kazuki

Deep learning (DL) has become a driving force and has been widely adopted in many domains and applications with competitive performance. In practice, to solve the nontrivial and complicated tasks in real-world applications, DL is often not used stand

Externí odkaz: http://arxiv.org/abs/2212.06828

Zobrazit plný text záznamu

Report

Verifying Attention Robustness of Deep Neural Networks against Semantic Perturbations

Autor: Munakata, Satoshi, Urban, Caterina, Yokoyama, Haruki, Yamamoto, Koji, Munakata, Kazuki

It is known that deep neural networks (DNNs) classify an input image by paying particular attention to certain specific pixels; a graphical representation of the magnitude of attention to each pixel is called a saliency-map. Saliency-maps are used to

Externí odkaz: http://arxiv.org/abs/2207.05902

Zobrazit plný text záznamu

Report

NeuRecover: Regression-Controlled Repair of Deep Neural Networks with Training History

Autor: Tokui, Shogo, Tokumoto, Susumu, Yoshii, Akihito, Ishikawa, Fuyuki, Nakagawa, Takao, Munakata, Kazuki, Kikuchi, Shinji

Systematic techniques to improve quality of deep neural networks (DNNs) are critical given the increasing demand for practical applications including safety-critical ones. The key challenge comes from the little controllability in updating DNNs. Retr

Externí odkaz: http://arxiv.org/abs/2203.00191

Zobrazit plný text záznamu

Report

AugmentedCode: Examining the Effects of Natural Language Resources in Code Retrieval Models

Autor: Bahrami, Mehdi, Shrikanth, N. C., Mizobuchi, Yuji, Liu, Lei, Fukuyori, Masahiro, Chen, Wei-Peng, Munakata, Kazuki

Code retrieval is allowing software engineers to search codes through a natural language query, which relies on both natural language processing and software engineering techniques. There have been several attempts on code retrieval from searching sn

Externí odkaz: http://arxiv.org/abs/2110.08512

Zobrazit plný text záznamu

Report

PyTorrent: A Python Library Corpus for Large-scale Language Models

Autor: Bahrami, Mehdi, Shrikanth, N. C., Ruangwan, Shade, Liu, Lei, Mizobuchi, Yuji, Fukuyori, Masahiro, Chen, Wei-Peng, Munakata, Kazuki, Menzies, Tim

A large scale collection of both semantic and natural language resources is essential to leverage active Software Engineering research areas such as code reuse and code comprehensibility. Existing machine learning models ingest data from Open Source

Externí odkaz: http://arxiv.org/abs/2110.01710

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Observation of cosmic-ray modulation and relativistic electron precipitation events with CALET

Autor: 他CALETチーム, MIYAKE, Shoko, KATAOKA, Ryuho, MUNAKATA, Kazuki, ASAOKA, Yoichi, NAKAHIRA, Satoshi, TORII, Shoji, TERASAWA, Toshio, AKAIKE, Yosui, KOBAYASHI, Kaneyoshi, CALET Team et al.

Publikováno v: 第21回宇宙科学シンポジウム講演集 = Proceedings of the 21st Space Science Symposium.

第21回宇宙科学シンポジウム (2021年1月6日-7日. オンライン開催)
21st Space Science Symposium (January 6-7, 2021. Online Meeting)
資料番号: SA6000163072
レポート番号: g07-4

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=jairo_______::84fe2f6e1e1ccfed61390b6c60ceeb4a
http://id.nii.ac.jp/1696/00047870/

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Vyhledávací nástroje:

Upřesnit hledání