Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
RCS |
2021-06-23 09:40 |
Online |
Online |
A Comparison of Variational Bayesian and Expectation Propagation Methods for Massive MIMO Signal Detection Hiroki Asumi, Junichiro Hagiwara, Toshihiko Nishimura, Takeo Ohgane, Yasutaka Ogawa, Takanori Sato (Hokkaido Univ.) RCS2021-30 |
Signal detection in massive MIMO has difficulty in reducing computational complexity as the number of antennas increases... [more] |
RCS2021-30 pp.7-12 |
R |
2021-06-12 14:25 |
Online |
Online (Zoom) |
A Study on Dual-task VAE with Weibull distribution for RUL estimation and application to Aero-Propulsion System data Ryosuke Sato, Mitsuhiro Kimura (Hosei Univ.) R2021-12 |
Remaining Useful Life (RUL) is one of the most important assessment measures in reliability engineering.
Although sever... [more] |
R2021-12 pp.7-12 |
ED, SDM, CPM |
2021-05-27 16:30 |
Online |
Online |
Variational Quantum Eigensolver Using Noisy Quantum Devices Tsukasa Miki, Moe Shimada, Ryo Okita, Jun-ichi Shirakashi (Tokyo Univ. of Agr. & Tech.) ED2021-8 CPM2021-8 SDM2021-19 |
(To be available after the conference date) [more] |
ED2021-8 CPM2021-8 SDM2021-19 pp.31-34 |
MI |
2021-03-16 09:30 |
Online |
Online |
Statistical modeling of pulmonary vasculatures in CT volumes using a deep generative model Yuki Saeki, Atshushi Saito (TUAT), Jean Cousty, Yukiko Kenmochi (LIGM/ UGE/ CNRS/ ESIEE Paris), Akinobu Shimizu (TUAT) MI2020-65 |
The purpose of this study is to build a statistical intensity model of pulmonary vasculatures in CT volumes. In this stu... [more] |
MI2020-65 pp.80-81 |
PRMU |
2020-12-18 11:15 |
Online |
Online |
Supervised disentangled representation learning
-- Disentangling features using classifier -- Shujiro Kuroda, Toshikazu Wada (Wakayama Univ.) PRMU2020-58 |
VAE is a DNN model for unsupervised representation learning. VAE learns to extract features from the input data as laten... [more] |
PRMU2020-58 pp.116-121 |
SP, EA, SIP |
2020-03-03 09:00 |
Okinawa |
Okinawa Industry Support Center (Cancelled but technical report was issued) |
Cross-Lingual Voice Conversion using Cyclic Variational Auto-encoder Hikaru Nakatani, Patrick Lumban Tobing, Kazuya Takeda, Tomoki Toda (Nagoya Univ.) EA2019-139 SIP2019-141 SP2019-88 |
In this report, we present a novel cross-lingual voice conversion (VC) method based on cyclic variational auto-encoder (... [more] |
EA2019-139 SIP2019-141 SP2019-88 pp.219-224 |
SP, EA, SIP |
2020-03-03 09:00 |
Okinawa |
Okinawa Industry Support Center (Cancelled but technical report was issued) |
Semi-supervised Self-produced Speech Enhancement and Suppression Based on Joint Source Modeling of Air- and Body-conducted Signals Using Variational Autoencoder Shogo Seki, Moe Takada, Kazuya Takeda, Tomoki Toda (Nagoya Univ.) EA2019-140 SIP2019-142 SP2019-89 |
This paper proposes a semi-supervised method for enhancing and suppressing self-produced speech, using a variational aut... [more] |
EA2019-140 SIP2019-142 SP2019-89 pp.225-230 |
EA |
2019-12-13 13:00 |
Fukuoka |
Kyushu Inst. Tech. |
Speaker-independent source separation with multichannel variational autoencoder Li Li (Univ. Tsukuba), Hirokazu Kameoka (NTT), Shota Inoue, Shoji Makino (Univ. Tsukuba) EA2019-77 |
The multichannel variational autoencoder method (MVAE) is a recently proposed determined source separation method, which... [more] |
EA2019-77 pp.79-84 |
IT |
2019-07-25 14:25 |
Tokyo |
NATULUCK-Iidabashi-Higashiguchi Ekimaeten |
Bayes Optimal Prediction and Its Approximative Algorithm on Model Including Cluster Explanatory Variables and Regression Explanatory Variables Haruka Murayama, Shota Saito, Yuta Nakahara, Toshiyasu Matsushima (Waseda Univ.) IT2019-16 |
In this research, data are assumed to be divided in clusters based on a part of the continuous explanatory variables, an... [more] |
IT2019-16 pp.5-10 |
NC, IBISML, IPSJ-MPS, IPSJ-BIO [detail] |
2019-06-17 16:15 |
Okinawa |
Okinawa Institute of Science and Technology |
Imputation of Missing Time-Series Multimodal Data with Variational Autoencoder Ryoichi Kojima, Shinya Wada, Kiyohito Yoshihara (KDDI Research) IBISML2019-8 |
Data is often missing and that results in negative effects on subsequent data analysis and creating machine learning mod... [more] |
IBISML2019-8 pp.51-55 |
EA, SIP, SP |
2019-03-15 13:30 |
Nagasaki |
i+Land nagasaki (Nagasaki-shi) |
[Poster Presentation]
An Evaluation of Underdetermined Source Separation Based on Multichannel Variational Autoencoder Shogo Seki (Nagoya Univ.), Hirokazu Kameoka (NTT), Li Li (Univ. Tsukuba), Tomoki Toda, Kazuya Takeda (Nagoya Univ.) EA2018-154 SIP2018-160 SP2018-116 |
This paper deals with a multichannel audio source separation problem under underdetermined conditions. Multichannel Non-... [more] |
EA2018-154 SIP2018-160 SP2018-116 pp.323-328 |
IBISML |
2019-03-05 14:30 |
Tokyo |
RIKEN AIP |
Efficient Exploration by Variational Information Maximizing Exploration on Reinforcement Learning Kazuki Doi, Keigo Okawa (Gifu Univ.), Motoki Shiga (Gifu Univ./JST/RIKEN) IBISML2018-107 |
In reinforcement learning,the policy function may not be optimized properly if the observed state space is limited to lo... [more] |
IBISML2018-107 pp.17-22 |
NC, MBE (Joint) |
2019-03-04 15:45 |
Tokyo |
University of Electro Communications |
Variational Bayes algorithm of region base coupled MRF with hidden phase variables Naoki Wada (Tokyo Inst. of Tech.), Masaichiro Mizumaki (JASRI), Yoshiki Seno (Saga prefectural regional industry support center), Masato Okada (The Univ. of Tokyo), Akai Ichiro (Kumamoto Univ.), Toru Aonishi (Tokyo Inst. of Tech.) NC2018-59 |
There are two methods in coupled Markov Random Field(MRF) model for image segmentation: edge-based method and region-bas... [more] |
NC2018-59 pp.87-92 |
IBISML |
2018-11-05 15:10 |
Hokkaido |
Hokkaido Citizens Activites Center (Kaderu 2.7) |
[Poster Presentation]
Inference for Logitistic Regression Mixture Model with Local Variational Approximation and Study for Variational Free Energy Fumito Nakamura, Ryosuke Konishi (Generic Solution), Yasushi Kiyoki (Keio) IBISML2018-48 |
A logistic regression mixture model (LRMM) is a mixed model of the Logistic regression model, and it is widely used in t... [more] |
IBISML2018-48 pp.29-36 |
IBISML |
2018-11-05 15:10 |
Hokkaido |
Hokkaido Citizens Activites Center (Kaderu 2.7) |
[Poster Presentation]
Variational Approximation Accuracy in Non-negative Matrix Factorization Naoki Hayashi (MSI) IBISML2018-51 |
The asymptotic behavior of the variational free energy of the non-negative matrix factorization (NMF) has been elucidate... [more] |
IBISML2018-51 pp.53-60 |
IBISML |
2018-11-05 15:10 |
Hokkaido |
Hokkaido Citizens Activites Center (Kaderu 2.7) |
[Poster Presentation]
Online Prediction for Varying Bernoulli Processes by Minimax Strategy Kenta Konagayoshi, Kazuho Watanabe (Toyohashi Tech) IBISML2018-61 |
Online prediction methods sequentially predict furure data from time series data. Since online pre-
diction does not ne... [more] |
IBISML2018-61 pp.127-134 |
IBISML |
2018-11-05 15:10 |
Hokkaido |
Hokkaido Citizens Activites Center (Kaderu 2.7) |
[Poster Presentation]
Comparison of Bayes estimation and variational Bayes estimation in mixed normal distribution model Tomofumi Nakayama, Naoki Fujii (UT), Kenji Nagata (AIST/JST PRESTO), Masato Okada (UT) IBISML2018-82 |
In Gaussian Mixture Model (GMM), Bayesian estimation is one of the estimation methods, but analyti- cal calculation is d... [more] |
IBISML2018-82 pp.287-292 |
AI |
2018-08-27 15:50 |
Osaka |
|
Bayesian Inference for Field of Physical Quantity from Data obtained at several Locations Masato Ota, Takeshi Okadome (KG Univ.) AI2018-23 |
This paper proposes a novel method for estimating the physical quantity at every location (physical quan- tity field) fr... [more] |
AI2018-23 pp.55-60 |
SIP, EA, SP, MI (Joint) [detail] |
2018-03-19 10:25 |
Okinawa |
|
Non-parallel and Many-to-Many Voice Conversion Using Variational Autoencoder Conditioned by Phonetic Posteriorgrams and d-vectors Yuki Saito (NTT/Univ. of Tokyo), Yusuke Ijima, Kyosuke Nishida (NTT), Shinnosuke Takamichi (Univ. of Tokyo) EA2017-105 SIP2017-114 SP2017-88 |
This paper proposes novel frameworks for non-parallel and many-to-many voice conversion (VC) using variational autoencod... [more] |
EA2017-105 SIP2017-114 SP2017-88 pp.21-26 |
PRMU, BioX |
2018-03-18 16:10 |
Tokyo |
|
Toward image inbetweening using Latent Model Paulino Cristovao (Univ. of Tsukuba), Yusuke Tanimura, Hidemoto Nakada, Hideki Asoh (AIST) BioX2017-49 PRMU2017-185 |
Image interpolation is a well known problem in computer vision. Many approaches are restricted to optical flow and convo... [more] |
BioX2017-49 PRMU2017-185 pp.79-84 |