Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
EA |
2024-05-22 14:15 |
Online |
Online |
未定
-- 未定 -- Tsubasa Ochiai (NTT), Kazuma Iwamoto (Doshisha Univ.), Marc Delcroix, Rintaro Ikeshita, Hiroshi Sato, Shoko Araki (NTT), Shigeru Katagiri (Doshisha Univ.) |
(To be available after the conference date) [more] |
|
RCC, ISEC, IT, WBS |
2024-03-14 13:00 |
Osaka |
Osaka Univ. (Suita Campus) |
[Special Invited Talk]
Smart Radio and Reliable Communication & Control
-- A Journey Through Research and Emerging Challenges -- Masaaki Katayama (Nagoya Univ.) RCS2023-276 SR2023-99 SRW2023-63 IT2023-117 ISEC2023-116 WBS2023-105 RCC2023-99 |
In Smart Radio, traditional hard-fixed circuits are realized using flexible devices and computers, marking the integrati... [more] |
RCS2023-276 SR2023-99 SRW2023-63 IT2023-117 ISEC2023-116 WBS2023-105 RCC2023-99 p.125(RCS), p.57(SR), p.90(SRW), p.266(ISEC), p.266(WBS), p.266(RCC) |
IN, IA (Joint) |
2023-12-22 15:00 |
Hiroshima |
Satellite Campus Hiroshima |
[Short Paper]
A Study on the Applicability of Graph Reduction to Evaluating the Robustness of Complex Networks Murakawa Yamato, Ryotaro Matsuo, Ryo Nakamura (Fukuoka Univ.) IA2023-53 |
Generally, the computational complexity of network simulation and machine learning based on graph structure such as GNN ... [more] |
IA2023-53 pp.48-52 |
SS, DC |
2023-10-12 10:25 |
Nagano |
(Primary: On-site, Secondary: Online) |
Robustness trends of DP-SGD, a machine learning with differential privacy Takahiro Kanki, Shinpei Ogata, Kozo Okano (Sinshu Univ), Shin Nakajima (NII) SS2023-28 DC2023-34 |
Although machine learning has been successful in various fields, there is a problem that an adversary can extract traini... [more] |
SS2023-28 DC2023-34 pp.38-43 |
NC, MBE (Joint) |
2023-03-15 11:20 |
Tokyo |
The Univ. of Electro-Communications (Primary: On-site, Secondary: Online) |
Optimizing SOINN Space for High-Dimensional Data Robustness Yu Takahagi, Yusuke Tsuchida, Yukari Yamauchi (Nihon Univ.) NC2022-112 |
Yamazaki et al. proposed a learning method called Self-Organizing Incremental Neural Network (SOINN). This method is an ... [more] |
NC2022-112 pp.113-118 |
HWS, VLD |
2023-03-02 14:15 |
Okinawa |
(Primary: On-site, Secondary: Online) |
[Memorial Lecture]
DependableHD: A Hyperdimensional Learning Framework for Edge-oriented Voltage-scaled Circuits [Memorial lecture] Dehua Liang (Osaka Univ.), Hiromitsu Awano (Kyoto Univ.), Noriyuki Miura, Jun Shiomi (Osaka Univ.) VLD2022-93 HWS2022-64 |
Voltage scaling is a promising approach for energy efficiency but also brings challenges to guaranteeing stable circuit ... [more] |
VLD2022-93 HWS2022-64 p.111 |
IT, EMM |
2022-05-17 15:05 |
Gifu |
Gifu University (Primary: On-site, Secondary: Online) |
Generating patch-wise adversarial examples for avoidance of face recognition system and verification of its robustness Hiroto Takiwaki, Minoru Kuribayashi, Nobuo Funabiki (Okayama univ.) IT2022-5 EMM2022-5 |
Advances in machine learning technologies such as Convolutional Neural Networks (CNN) have made it possible to identify ... [more] |
IT2022-5 EMM2022-5 pp.23-28 |
IBISML |
2022-03-08 10:25 |
Online |
Online |
Robust computation of optimal transport by β-potential regularization Shintaro Nakamura (Univ. Tokyo), Han Bao (Univ.Tokyo/RIKEN), Masashi Sugiyama (RIKEN/Univ. Tokyo) IBISML2021-31 |
Optimal transport (OT) has become a widely used tool to measure the discrepancy between probability distributions
in th... [more] |
IBISML2021-31 pp.8-14 |
IE, ITS, ITE-AIT, ITE-ME, ITE-MMS [detail] |
2022-02-22 13:15 |
Online |
Online |
Noise-Resistant Learning for Object Detection Jiafeng Mao, Qing Yu, Yoko Yamakata, Kiyoharu Aizawa (UTokyo) ITS2021-52 IE2021-61 |
Supervised training of object detectors requires well-annotated large-scale datasets, whose production is extremely expe... [more] |
ITS2021-52 IE2021-61 pp.163-166 |
SeMI |
2022-01-20 14:20 |
Nagano |
(Primary: On-site, Secondary: Online) |
[Short Paper]
Estimation of Sound Environment in Room by applying to Transfer Learning using Spectrograms Images Shota Sano, Yuusuke Kawakita, Tsuyoshi Miyazaki, Hiroshi Tanaka (KAIT) SeMI2021-57 |
A variety of environmental sounds exist in a room, and the classification of these sounds can be expected to have variou... [more] |
SeMI2021-57 pp.22-25 |
NC, IBISML, IPSJ-BIO, IPSJ-MPS [detail] |
2021-06-28 15:45 |
Online |
Online |
Active learning for distributionally robust chance-constrained optimization Yu Inatsu, Shion Takeno, Masayuki Karasuyama (Nitech), Ichiro Takeuchi (Nitech/RIKEN) NC2021-7 IBISML2021-7 |
Chance-constrained optimization (CCO) is one of the constrained optimization problems where some of the inputs to a blac... [more] |
NC2021-7 IBISML2021-7 pp.47-54 |
IBISML |
2021-03-02 10:00 |
Online |
Online |
Learning from Noisy Complementary Labels with Robust Loss Functions Hiroki Ishiguro (UTokyo), Takashi Ishida (UTokyo/RIKEN), Masashi Sugiyama (RIKEN/UTokyo) IBISML2020-34 |
It has been demonstrated that large-scale labeled datasets facilitate the success of machine learning. However, collecti... [more] |
IBISML2020-34 pp.1-8 |
PRMU, IPSJ-CVIM |
2020-03-16 15:25 |
Kyoto |
(Cancelled but technical report was issued) |
Assessing robustness of deep learning methods in dermoscopic workflow Sourav Mishra (Univ. of Tokyo), Hideaki Imaizumi (exMedio), Toshihiko Yamasaki (Univ. of Tokyo) PRMU2019-79 |
Our paper aims to evaluate current deep learning methods for clinical workflow in the domain of dermatology. Although de... [more] |
PRMU2019-79 pp.77-78 |
PRMU, IPSJ-CVIM |
2020-03-17 09:45 |
Kyoto |
(Cancelled but technical report was issued) |
Deep neural network representation and learning of low-rank and sparse approximation
-- With application to celiac angiography under free breathing -- Ryohei Miyoshi, Tomoya Sakai (Nagasaki Univ.), Takashi Ohnishi, Hideaki Haneishi (Chiba Univ.) PRMU2019-91 |
Low-rank and sparse (L+S) approximation, a.k.a. stable and robust principal component analysis, is known to be suitable ... [more] |
PRMU2019-91 pp.133-138 |
MSS, NLP (Joint) |
2020-03-10 15:45 |
Aichi |
(Cancelled but technical report was issued) |
Temporal Logic Falsification for Simulink models based on the hybrid robustness using ChainerRL Ryota Owaki, Shoji Yuen (NU) MSS2019-67 |
We present a method of falsification for the hybrid property of Simulink model using deep reinforcement learning. This s... [more] |
MSS2019-67 pp.53-58 |
SSS |
2019-09-24 15:15 |
Tokyo |
|
A Proposal of Detection Method of Adversalial Examples based on Frequency Domain Yuya Kase, Masaomi Kimura (SIT) SSS2019-20 |
We propose a detection method of special data Adversarial Examples that cause misclassification of neural networks. Adve... [more] |
SSS2019-20 pp.13-16 |
MSS, CAS, IPSJ-AL [detail] |
2018-11-12 17:15 |
Shizuoka |
|
[Invited Talk]
Robust Optimization and its Application to Supervised Learning Akiko Takeda (U.Tokyo) CAS2018-67 MSS2018-43 |
There are various uncertainties in real-world problems. When formulating them as mathematical optimization problems, we ... [more] |
CAS2018-67 MSS2018-43 p.55 |
IBISML |
2018-11-05 15:10 |
Hokkaido |
Hokkaido Citizens Activites Center (Kaderu 2.7) |
[Poster Presentation]
Generalized Dirichlet-Process-Means with f-Mean and Analysis of Influence Function Masahiro Kobayashi, Kazuho Watanabe (Toyohashi Tech.) IBISML2018-50 |
DP-means clustering was obtained as an extension of $K$-means clustering. While it is implemented with a simple and effi... [more] |
IBISML2018-50 pp.45-52 |
IT |
2016-12-13 15:50 |
Gifu |
Takayama Green Hotel |
[Invited Talk]
Bregman Divergence and its Applications Takafumi Kanamori (Nagoya Univ.) IT2016-44 |
In statistical inference and machine learning, Bregman divergences are often used. This paper shows applications of Breg... [more] |
IT2016-44 pp.15-20 |
IBISML |
2016-11-16 15:00 |
Kyoto |
Kyoto Univ. |
Robust supervised learning under uncertainty in dataset shift Weihua Hu, Issei Sato (UTokyo), Masashi Sugiyama (RIKEN/UTokyo) IBISML2016-50 |
When machine learning is deployed in the real world, its performance can be significantly undermined because test data m... [more] |
IBISML2016-50 pp.37-44 |