Výsledky vyhledávání - "Tomoyuki Myojin"

Guidelines for Quality Assurance of Machine Learning-Based Artificial Intelligence

Autor: Koichi Hamada, Tomoyuki Myojin, Satoshi Masuda, Takahiro Toku, Susumu Tokumoto, Kazunori Tsuchiya, Mineo Matsuya, Yasuhiro Ujita, Hideto Ogawa, Fuyuki Ishikawa, Gaku Fujii, Yasuharu Nishi

Publikováno v: International Journal of Software Engineering and Knowledge Engineering. 30:1589-1606

Significant effort is being put into developing industrial applications for artificial intelligence (AI), especially those using machine learning (ML) techniques. Despite the intensive support for building ML applications, there are still challenges

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::9dd85f5dc763d1633d1f3846ebb026f7
https://doi.org/10.1142/s0218194020400227

Zobrazit plný text záznamu

Detecting Uncertain BNN Outputs on FPGA Using Monte Carlo Dropout Sampling

Autor: Tomoyuki Myojin, Shintaro Hashimoto, Naoki Ishihama

Publikováno v: Artificial Neural Networks and Machine Learning – ICANN 2020 ISBN: 9783030616151
ICANN (2)

Monte Carlo dropout sampling (MC Dropout), which approximates a Bayesian Neural Network, is useful for measuring the uncertainty in the output of a Deep Neural Network (DNN). However, because it takes a long time to sample DNN’s output for calculat

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::41ef73a44f23df5fe7a317f342a50c92
https://doi.org/10.1007/978-3-030-61616-8_3

Zobrazit plný text záznamu

Improving Reliability of Object Detection for Lunar Craters Using Monte Carlo Dropout

Autor: Naoki Ishihama, Shintaro Hashimoto, Keisuke Sugawara, Tomoyuki Myojin, Kenji Mori

Publikováno v: Lecture Notes in Computer Science ISBN: 9783030305079
ICANN (3)

In the task of detecting craters on the lunar surface, some craters were difficult to detect correctly, and a Deep Neural Network (DNN) could not represent the uncertainty of such detection. However, a measure of uncertainty could be expressed as the

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::2e141306594a3edee99249d220c7677a
https://doi.org/10.1007/978-3-030-30508-6_6

Zobrazit plný text záznamu

A Model-Checking Approach for Fault Analysis Based on Configurable Model Extraction

Autor: Makoto Ichii, Yuichiroh Nakagawa, Tomoyuki Myojin, Hideto Ogawa, Masaki Chikahisa

Publikováno v: IEICE Transactions on Information and Systems. :1150-1160

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::9d74f9b263968148e4439a0d1f0c7394
https://doi.org/10.1587/transinf.2014fop0012

Zobrazit plný text záznamu

Case study of applying SPLE to development of network switch products

Autor: Tomoyuki Myojin, Tadahisa Kato, Koji Hirono, Takashi Hasegawa, Kawakami Masumi, Hideto Ogawa

Publikováno v: SPLC

Software product line engineering has spread as a technique for promoting the efficient development of embedded products with many product line-ups. During the development of network switch products at Hitachi Metals, Ltd., the number of development

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::a91c6c45adf5e1f1af8ae45283fbcca4
https://doi.org/10.1145/2491627.2491636

Zobrazit plný text záznamu

A Rule-based Automated Approach for Extracting Models from Source Code

Autor: Hideto Ogawa, Tomoyuki Myojin, Masaki Chikahisa, Yuichiroh Nakagawa, Makoto Ichii

Publikováno v: WCRE

We herein propose Program-oriented Modeling (POM), a novel approach to extract software models automatically from source code. The proposed approach is developed in order to satisfy the requirements of model abstraction for situations in which a mode

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::6f169090ebda655973b3a0e3fb97ac06
https://doi.org/10.1109/wcre.2012.40

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání