Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
RCC, ISEC, IT, WBS |
2024-03-14 17:00 |
Osaka |
Osaka Univ. (Suita Campus) |
Comparison of Scale Parameter Dependence of Estimation Performance in Sparse Bayesian Linear Regression Model with Variance Gamma Prior Distribution and t-Prior Distribution Kazuaki Murayama (UEC) IT2023-135 ISEC2023-134 WBS2023-123 RCC2023-117 |
In the sparse estimation with linear regression model, the variance gamma distribution and t-distribution can be used as... [more] |
IT2023-135 ISEC2023-134 WBS2023-123 RCC2023-117 pp.374-379 |
NC, IBISML, IPSJ-BIO, IPSJ-MPS [detail] |
2022-06-27 14:25 |
Okinawa |
(Primary: On-site, Secondary: Online) |
A Bagging Method to Improve the Accuracy of Gaussian Process Regression for Neural Architecture Search Rion Hada, Masao Okita, Fumihiko Ino (Osaka Univ.) NC2022-2 IBISML2022-2 |
The goal of this study is to improve performance estimation for neural network architectures in neural architecture sear... [more] |
NC2022-2 IBISML2022-2 pp.6-13 |
PRMU, IPSJ-CVIM |
2020-03-17 16:50 |
Kyoto |
(Cancelled but technical report was issued) |
Experimental Evaluation for Bayes Error Estimation Capability of Large Geometric Margin Minimum Classification Error Training Ikuhiro Nishiyama (Doshisha Univ.), Hideyuki Watanabe (ATR), Shigeru Katagiri, Miho Ohsaki (Doshisha Univ.) PRMU2019-99 |
Previous studies suggested that the Large Geometric Margin-Minimum Classification Error (LGM-MCE) training method had th... [more] |
PRMU2019-99 pp.231-236 |
IBISML |
2020-01-09 13:25 |
Tokyo |
ISM |
Real Log Canonical Threshold of Three Layered Neural Network with Swish Activation Function Raiki Tanaka, Sumio Watanabe (Tokyo Tech) IBISML2019-19 |
In neural network learning, it is known that selection of activation function effects generalization performance. Althou... [more] |
IBISML2019-19 pp.9-15 |
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 |
EA, ASJ-H |
2017-11-30 11:00 |
Overseas |
University of Auckland (New Zealand) |
Fuzzy Bayesian Filter for Sound Environment by Considering Additive Property of Energy Variable and Fuzzy Observation in Decibel Scale Akira Ikuta (Prefectural Univ. of Hiroshima), Hisako Orimoto (Prefectural Univ. or Hiroshima) EA2017-61 |
In the measurement and evaluation of actual random phenomena in a sound environment system, the observed data often cont... [more] |
EA2017-61 pp.19-24 |
IT, SIP, RCS |
2017-01-20 11:15 |
Osaka |
Osaka City Univ. |
Performance of L1 regularized channel estimation techniques using information criteria Yasuhiro Takano (Kobe Univ.) IT2016-85 SIP2016-123 RCS2016-275 |
Most $ell1$ regularized channel estimation techniques assume that degree of sparsity (DoS) is known. The variance of cha... [more] |
IT2016-85 SIP2016-123 RCS2016-275 pp.227-230 |
CCS |
2015-11-10 15:00 |
Kyoto |
Inamori Foundation Memorial Building, Kyoto Univ. |
Segmental Bayesian estimation of neuronal parameters from spike trains Isao Tokuda, Huu Hoang (Ritsumeikan Univ.) CCS2015-63 |
Multi-electrode recording is now a common technique to simultaneously collect neuronal spike data of a population of the... [more] |
CCS2015-63 pp.99-102 |
PRMU |
2013-06-11 16:00 |
Tokyo |
|
Criterion for image stitching based on the intensity distribution and entropy Kenta Matsui, Kazuaki Kondo, Takahiro Koizumi, Yuichi Nakamura (Kyoto Univ.) PRMU2013-32 |
In this paper, we propose a criteria of image stitching to acquire larger panoramic images from first person view videos... [more] |
PRMU2013-32 pp.77-82 |
MI |
2012-07-19 15:40 |
Yamagata |
Yamagata Univ. |
Bayesian Inference Approach to Visualize Neuroreceptor Density using Positron Emission Tomography without Arterial Blood Sampling Takahiro Kozawa, Hidekata Hontani (NIT), Kazuya Sakaguchi (Kitasato Univ), Muneyuki Sakata (TMGHIG), Yuichi Kimura (NIRS) MI2012-26 |
A Bayesian approach to de-noise tissue time activity curves (tTAC) is proposed in order to quantitatively visualize neur... [more] |
MI2012-26 pp.29-34 |
EMM, ISEC, SITE, ICSS, IPSJ-CSEC, IPSJ-SPT [detail] |
2012-07-19 13:30 |
Hokkaido |
|
Performance evaluation of digital watermarking model with image restoration
-- image restoration using 2D Ising model -- Masaki Kawamura (Yamaguchi Univ.), Tatsuya Uezu (Nara Women's Univ.), Masato Okada (Univ. Tokyo) ISEC2012-13 SITE2012-9 ICSS2012-15 EMM2012-5 |
We evaluate the decoding performance in the case that the prior probability is given by 2D Ising model in a spread spect... [more] |
ISEC2012-13 SITE2012-9 ICSS2012-15 EMM2012-5 pp.29-34 |
NC, MBE (Joint) |
2011-03-08 09:50 |
Tokyo |
Tamagawa University |
A Theoretical Analysis of KL-type Generalization Error on Hidden Variable Distribution Keisuke Yamazaki (Tokyo Inst. of Tech.) NC2010-165 |
In information science, hierarchical models such as mixture models,
hidden Markov models and Bayesian networks are wide... [more] |
NC2010-165 pp.223-228 |
NC, MBE (Joint) |
2010-03-09 14:35 |
Tokyo |
Tamagawa University |
Localization of Robots Based on Learning of Filters for Image features Mariko Oki, Masumi Ishikawa (Kyushu Inst. of Tech.) NC2009-107 |
In feature-based localization of a mobile robot, it is difficult to decide what features to use for localization.To trai... [more] |
NC2009-107 pp.113-118 |
PRMU, SP, MVE, CQ |
2010-01-21 11:40 |
Kyoto |
Kyoto Univ. |
Online speaker clustering using an ergodic HMM and its application to meeting minute generation Takafumi Koshinaka, Kentaro Nagatomo, Kenji Satoh (NEC Corp.) CQ2009-62 PRMU2009-161 SP2009-102 MVE2009-84 |
A novel online speaker clustering method suitable for real-time applications is proposed. Using an ergodic hidden Marko... [more] |
CQ2009-62 PRMU2009-161 SP2009-102 MVE2009-84 pp.39-44 |
NC, MBE (Joint) |
2009-12-11 17:00 |
Aichi |
|
On the estimating method of the information rates of retinal ganglion cells Hiroki Saito, Yoshimi Kamiyama (Aichi Prefectural Univ) NC2009-69 |
Mutual information is often used to quantify the response property of retinal ganglion cells to sensory inputs. To calcu... [more] |
NC2009-69 pp.37-42 |
NC |
2009-10-24 10:40 |
Saga |
Saga University |
Mean-field theoretical approach to Bayesian estimation of motion velocity vector in successive digital images Yuya Inagaki, Jun-ichi Inoue (Hokkaido Univ.) NC2009-44 |
We examine a mean-field iterative aigorithm to estimate motion velocity vector fields in successive digital images based... [more] |
NC2009-44 pp.41-46 |
PRMU |
2009-03-13 15:20 |
Miyagi |
Tohoku Institute of Technology |
A Proposal of Ensemble-based Minimum Classification Error Training Hideyuki Watanabe (NICT/ATR), Shigeru Katagiri, Kohta Yamada (Doshisha Univ.), Atsushi Nakamura, Erik McDermott, Shinji Watanabe (NTT), Shin'ichi Taniguchi, Naho Nishijima, Miho Ohsaki (Doshisha Univ.) PRMU2008-250 |
We propose an ensemble-based minimum classification error (MCE) training method to combine multiple weak classifiers in ... [more] |
PRMU2008-250 pp.71-76 |
NC |
2009-01-19 13:30 |
Hokkaido |
Hokkaido Univ. |
Structure estimation using time-dependent data in hidden Markov models Masashi Matsumoto, Sumio Watanabe (Tokyo Inst. of Tech.) NC2008-86 |
A lot of learning machines used in information science, for example, mixture models, artificial neural networks, Bayesia... [more] |
NC2008-86 pp.25-30 |
MBE, NC (Joint) |
2007-12-22 10:50 |
Aichi |
|
Generalization and Trainining Errors of Bayes and Gibbs Estimations in Singular Sumio Watanabe (Tokyo Inst. of Tech.) NC2007-75 |
In singular learning machines such as neural networks, normal mixtures,
Bayesian networks, and reduced rank regressions... [more] |
NC2007-75 pp.25-30 |
NC |
2007-10-18 09:55 |
Miyagi |
Tohoku University |
Variational Bayes Hidden Markov Models for extracting spatiotemporal spike pattern Kentaro Katahira (Univ. Tokyo/RIKEN), Jun Nishikawa, Kazuo Okanoya (RIKEN), Masato Okada (Univ. Tokyo/RIKEN) NC2007-34 |
Hidden Markov Model (HMM) is used to extracting spatio-temporal pattern from spikes recorded by
multielectrode. The EM ... [more] |
NC2007-34 pp.7-12 |