Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
ITE-ME, ITE-IST, BioX, SIP, MI, IE [detail] |
2024-06-06 13:20 |
Niigata |
Nigata University (Ekinan-Campus "TOKIMATE") |
Enhanced Security with Random Binary Weights for Privacy-Preserving Federated Learning Hiroto Sawada, Shoko Imaizumi (Chiba Univ.), Hitoshi Kiya (TMU) |
(To be available after the conference date) [more] |
|
PRMU, IBISML, IPSJ-CVIM |
2024-03-04 09:12 |
Hiroshima |
Hiroshima Univ. Higashi-Hiroshima campus (Primary: On-site, Secondary: Online) |
Creating Adversarial Examples to Deceive Both Humans and Machine Learning Models Ko Fujimori (Waseda Univ.), Toshiki Shibahara (NTT), Daiki Chiba (NTT Security), Mitsuaki Akiyama (NTT), Masato Uchida (Waseda Univ.) PRMU2023-65 |
One of the vulnerability attacks against neural networks is the generation of Adversarial Examples (AE), which induce mi... [more] |
PRMU2023-65 pp.82-87 |
NS, IN (Joint) |
2024-03-01 11:35 |
Okinawa |
Okinawa Convention Center |
Application of a Deep Reinforcement Learning Algorithm to Virtual Machine Migration Control in Multi-Stage Information Processing Systems Yuki Kojitani (Okayama Univ.), Kazutoshi Nakane (Nagoya Univ.), Yuya Tarutani (Okayama Univ.), Celimuge Wu (UEC), Yusheng Ji (NII), Tokumi Yokohira (Okayama Univ.), Tutomu Murase (Nagoya Univ.), Yukinobu Fukushima (Okayama Univ.) IN2023-87 |
This paper tackles a virtual machine (VM) migration control problem to maximize the progress (accuracy) of information p... [more] |
IN2023-87 pp.130-135 |
CS, CQ (Joint) |
2023-05-18 15:10 |
Kagawa |
Rexxam Hall (Kagawa Kenmin Hall) (Primary: On-site, Secondary: Online) |
On the performance of sorting out invalid jobs in scheduling using the policy gradient method for deadline-aware jobs Tatusya Sagisaka, Kohei Shiomoto (TCU), Takashi Kurimoto (NII) CQ2023-1 |
When transferring data in the field of communication between data centers, existing methods such as Earliest Deadline Fi... [more] |
CQ2023-1 pp.1-6 |
RCS, SIP, IT |
2022-01-21 11:20 |
Online |
Online |
Deep-Unfolded Sparse Signal Recovery Algorithm using TopK Operator Masanari Mizutani (NITech), Satoshi Takabe (TITech), Tadashi Wadayama (NITech) IT2021-72 SIP2021-80 RCS2021-240 |
Compressed sensing for estimating sparse signals is formulated as an NP-hard problem, where LASSO based on convex relax... [more] |
IT2021-72 SIP2021-80 RCS2021-240 pp.245-251 |
SANE |
2021-11-12 14:50 |
Online |
Online |
GPR data processing methods based on extrem gradient boosting algorithm to detect the backfill grouting of shield tunnel Xiongyao Xie, Li Zeng, Biao Zhou (Tongji Univ.) SANE2021-59 |
Shield tunnel method is currently the most important method for tunnel excavation in soft soil areas. With the construct... [more] |
SANE2021-59 pp.144-148 |
IT |
2021-07-09 13:50 |
Online |
Online |
Projected gradient MIMO signal detection using Chebyshev step Asahi Mizukoshi, Tadashi Wadayama, Satoshi Takabe (NITech) IT2021-25 |
This paper proposes a projected gradient detection method using the Chebyshev steps for a signal detector in a MIMO (Mul... [more] |
IT2021-25 pp.57-62 |
EA, US, SP, SIP, IPSJ-SLP [detail] |
2021-03-03 10:25 |
Online |
Online |
Remote Sensing Data Restoration by Constraining the Gradients of Stripe Noise Kazuki Naganuma, Saori Takeyama, Shunsuke Ono (Titech) EA2020-60 SIP2020-91 SP2020-25 |
This paper proposes an effective and efficient restoration methods for remote-sensing data by constraining the gradient ... [more] |
EA2020-60 SIP2020-91 SP2020-25 pp.5-8 |
NC, MBE (Joint) |
2021-03-04 16:50 |
Online |
Online |
A3C with Deterministic Policy Gradient Yu Takahagi, Yukari Yamauchi (Nihon Univ.) NC2020-63 |
Mnih et al. proposed a learning method called Asynchronous Advantage Actor-Critic (A3C). This method explores asynchrono... [more] |
NC2020-63 pp.117-120 |
SIP |
2020-08-28 10:30 |
Online |
Online |
Improvement Convergence Rate of the Sign Algorithm by Natural Gradient Method Taiyo Mineo, Hayaru Shouno (UEC) SIP2020-34 |
In lossless audio compression, it is essential to predictive residuals to be sparse, since we apply entropy codings to r... [more] |
SIP2020-34 pp.19-24 |
PN |
2020-08-25 10:50 |
Online |
Online |
Policy Gradient-based Deep Reinforcement Learning for Deadline-aware Data Transfer over Wide Area Networks Masaki Notoya, Kohei Shiomoto (Tokyo City Univ.), Takashi Kurimoto (NII) PN2020-21 |
Deadline-aware job scheduling problems have been attracting attention in the application domains of scientific workflows... [more] |
PN2020-21 pp.49-56 |
MSS, NLP (Joint) |
2018-03-12 14:00 |
Osaka |
|
Learning in Two-Player Matrix Games by Policy Gradient Lagging Anchor Shiyao Ding, Toshimitsu Ushio (Osaka Univ.) MSS2017-79 |
We propose a novel multi-agent reinforcement learning (MARL) algorithm which is called a policy gra-
dient lagging anch... [more] |
MSS2017-79 pp.11-14 |
SIP, IT, RCS |
2018-01-22 13:55 |
Kagawa |
Sunport Hall Takamatsu |
Hyperspectral Image Restoration Ryuji Kurihara, Masahiro Okuda (Kitayu U.) IT2017-73 SIP2017-81 RCS2017-287 |
We propose a new regularization function for hyperspectral image (HSI) restoration. Spatial-smoothness-based regularizat... [more] |
IT2017-73 SIP2017-81 RCS2017-287 pp.107-111 |
EMM, IE, LOIS, IEE-CMN, ITE-ME [detail] |
2017-09-05 15:00 |
Kyoto |
Kyoto Univ. (Clock Tower Centennial Hall) |
Color group constraint for image smoothing Riku Mikami, Taichi Yoshida, Masahiro Iwahashi (Nagaoka Univ. of Tech.) LOIS2017-25 IE2017-46 EMM2017-54 |
$L_0$ gradient minimization is a technique that belongs to edge-preserving image smoothing. The objective function of $L... [more] |
LOIS2017-25 IE2017-46 EMM2017-54 pp.87-90 |
SIP, CAS, MSS, VLD |
2017-06-19 11:20 |
Niigata |
Niigata University, Ikarashi Campus |
An Optimization Method for Automotive Engine Control Parameters Using Gradient Methods Shogo Masuda, Shinobu Nagayama, Masato Inagi, Shin'ichi Wakabayashi (Hiroshima City Univ.) CAS2017-6 VLD2017-9 SIP2017-30 MSS2017-6 |
In this study, we address a problem to obtain optimum control parameters by computing an inverse image of the target out... [more] |
CAS2017-6 VLD2017-9 SIP2017-30 MSS2017-6 pp.31-36 |
IBISML |
2017-03-07 11:30 |
Tokyo |
Tokyo Institute of Technology |
A stochastic optimization method and generalization bounds for voting classifiers by continuous density functions Atsushi Nitanda (Tokyo Tech./NTTDATA MSI), Taiji Suzuki (Tokyo Tech./JST/RIKEN) IBISML2016-108 |
We consider a learning method for the majority vote classifier by probability measure on continuously parametrized space... [more] |
IBISML2016-108 pp.63-69 |
IBISML |
2016-11-17 14:00 |
Kyoto |
Kyoto Univ. |
[Poster Presentation]
Stochastic Particle Gradient Descent for the Infinite Majority Vote Classifier Atsushi Nitanda, Taiji Suzuki (Tokyo Tech.) IBISML2016-79 |
We consider a learning method for the infinite majority vote classifier combined by a density on a continuous space of b... [more] |
IBISML2016-79 pp.235-241 |
IBISML |
2016-11-17 14:00 |
Kyoto |
Kyoto Univ. |
Incremental Natural Actor Critic with Importance Weight Aware Update Ryo Iwaki (Osaka Univ.), Hiroki Yokoyama (Tamagawa Univ.), Minoru Asada (Osaka Univ.) IBISML2016-81 |
Appropriate tuning of step-size parameter is crucial for reinforcement learning, as well as other machine learning techn... [more] |
IBISML2016-81 pp.251-257 |
VLD |
2016-03-02 10:55 |
Okinawa |
Okinawa Seinen Kaikan |
Lithography Hotspot Detection Using Histogram of Oriented Light Propagation Yoichi Tomioka (UoA), Tetsuaki Matsunawa (Toshiba) VLD2015-136 |
In recent semiconductor manufacturing process, it is essential to detect and to remove lithography hotspots, which induc... [more] |
VLD2015-136 pp.143-148 |
PRMU, CNR |
2016-02-22 16:30 |
Fukuoka |
|
Eye Detection by using Gradient Value for Improvement Performance of Wearable Gaze Estimation System Chinsatit Warapon, Takeshi Saitoh (Kyutech) PRMU2015-163 CNR2015-64 |
This paper presents a fast and precious eye detection technique by using gradient value for improve the performance of w... [more] |
PRMU2015-163 CNR2015-64 pp.149-154 |