Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
MRIS, ITE-MMS |
2023-06-08 14:20 |
Miyagi |
Tohoku Univ. (RIEC) (Primary: On-site, Secondary: Online) |
[Invited Talk]
Computing in pursuit of energy efficiency
-- From the perspective of non-volatile memory circuits using MTJ -- Kimiyoshi Usami (Shibaura IT) MRIS2023-3 |
From AlphaGo which defeated a professional human GO player up to automatic driving of cars and the very recent ChatGPT, ... [more] |
MRIS2023-3 pp.13-20 |
RCS |
2022-06-16 14:55 |
Okinawa |
University of the Ryukyus, Senbaru Campus and online (Primary: On-site, Secondary: Online) |
A study on model parameters for MIMO signal detection using learned AMP Mari Miyoshi, Toshihiko Nishimura, Takanori Sato, Takeo Ohgane, Yasutaka Ogawa, Junichiro Hagiwara (Hokkaido Univ.) RCS2022-50 |
Approximate message passing (AMP) is applicable to massive MIMO signal detection and achieves a high detection performan... [more] |
RCS2022-50 pp.156-161 |
RCS |
2021-06-23 09:50 |
Online |
Online |
A basic study on signal detection using learned approximate message passing Mari Miyoshi, Wakaba Tsujimoto, Toshihiko Nishimura, Takeo Ohgane, Yasutaka Ogawa, Junichiro Hagiwara, Takanori Sato (Hokkaido Univ.) RCS2021-31 |
Approximate message passing (AMP) is applicable to massive MIMO signal detection and achieves a high detection performan... [more] |
RCS2021-31 pp.13-18 |
HWS, VLD [detail] |
2021-03-03 10:00 |
Online |
Online |
Energy Efficient Approximate Storing to MRAM for Deep Neural Network Tasks in Edge Computing Yoshinori Ono, Kimiyoshi Usami (SIT) VLD2020-67 HWS2020-42 |
On-chip learning is gaining attention in edge devices. In addition, a magnetic RAM (MRAM) is a promising memory technolo... [more] |
VLD2020-67 HWS2020-42 pp.1-6 |
RCS, SAT (Joint) |
2019-08-23 13:40 |
Aichi |
Nagoya University |
[Invited Lecture]
Past, Present, and Future of Message-Passing Demodulation Keigo Takeuchi (TUT) SAT2019-39 RCS2019-168 |
Approximate message-passing (AMP) is attractive iterative demodulation in the present academic research of massive multi... [more] |
SAT2019-39 RCS2019-168 pp.119-124(SAT), pp.117-122(RCS) |
RCS, SIP, IT |
2019-01-31 12:30 |
Osaka |
Osaka University |
Trainable ISTA
-- Deep learning-based iterative algorithm for sparse signal recovery -- Satoshi Takabe, Tadashi Wadayama (NITech) IT2018-45 SIP2018-75 RCS2018-252 |
(To be available after the conference date) [more] |
IT2018-45 SIP2018-75 RCS2018-252 pp.61-66 |
VLD, HWS (Joint) |
2018-02-28 09:30 |
Okinawa |
Okinawa Seinen Kaikan |
On Fast Computation of RBF Approximate Function by FPGA Implementation Shogo Masuda, Shinobu Nagayama, Masato Inagi, Shin'ichi Wakabayashi (Hiroshima City Univ.) VLD2017-89 |
Radial basis functions (RBFs) are used for function fitting (approximation) of discrete data in various fields such as m... [more] |
VLD2017-89 pp.1-6 |
IBISML |
2015-11-26 15:00 |
Ibaraki |
Epochal Tsukuba |
[Poster Presentation]
Approximate Distribution Followed by A Principal Component Term Corresponding with the Population Eigenvalue of zero value in the Q Statistic Yasuyuki Kobayashi (Teikyo Univ.) IBISML2015-52 |
The Mahalanobis distance requires all the population eigenvalues of the population covariance matrix larger than zero. H... [more] |
IBISML2015-52 pp.1-7 |
IBISML |
2015-11-27 14:00 |
Ibaraki |
Epochal Tsukuba |
[Poster Presentation]
Performance degradation of AMP for Ising perceptron when the system size is small Arise Kuriya, Toshiyuki Tanaka (Kyoto Univ.) IBISML2015-85 |
Approximate Massage Passing (AMP) algorithm, proposed by Donoho et al., is derived from Belief Propagation (BP) algorith... [more] |
IBISML2015-85 pp.241-247 |
IBISML |
2015-03-06 15:45 |
Kyoto |
Kyoto University |
Model selection with approximate validation error guarantee for (L^2_2) regularized convex loss minimization problems Atsushi Shibagaki, Yoshiki Suzuki, Ichiro Takeuchi (NIT) IBISML2014-96 |
In this paper we propose a new algorithm that can select an approximately optimal regularization parameter in a class of... [more] |
IBISML2014-96 pp.79-86 |
CQ, IMQ, MVE, IE (Joint) [detail] |
2015-03-04 11:40 |
Tokyo |
Seikei Univ. |
Fast Bag-of-Feature Generation Featuring Approximate Nearest Image-Patch Search Kei Ito, Toshihiko Yamasaki, Kiyoharu Aizawa (UT) IMQ2014-53 IE2014-114 MVE2014-101 |
In Bag-of-Features models, which have been widely used in object recognition, various speed-up approaches have been deve... [more] |
IMQ2014-53 IE2014-114 MVE2014-101 pp.125-126 |
COMP |
2014-12-05 15:25 |
Kumamoto |
Sojo University |
Homomorphism-Substitutable Context-free Languages and Learning Algorithm Takayuki Kuriyama (Sokendai/ NII) COMP2014-38 |
We generalized the class of $k,l$-substitutable languages (Yoshinala, 2008). Each language in the generalized class is c... [more] |
COMP2014-38 pp.37-44 |
IBISML |
2014-11-17 17:00 |
Aichi |
Nagoya Univ. |
[Poster Presentation]
Approximate Models of Probability Distributions for Principal Components of Sample Mahalanobis Distances
-- About Each Element and Partial Sum of Sample Mahalanobis Distances -- Yasuyuki Kobayashi (Teikyo Univ.) IBISML2014-37 |
Probability distributions of the principal components and their partial sum, into which a sample Mahalanobis distance is... [more] |
IBISML2014-37 pp.17-24 |
CPSY, DC (Joint) |
2014-07-30 09:25 |
Niigata |
Toki Messe, Niigata |
Instruction Execution Method towards Error Reduction of Neural Network Processing Kazuma Koike, Shinya Takamaeda-Yamazaki, Jun Yao, Yasuhiko Nakashima (NAIST) CPSY2014-33 |
Approximate Computing has attracted attention as a method for reducing power consumption in varies applications, such as... [more] |
CPSY2014-33 pp.137-142 |
IBISML |
2014-03-07 11:10 |
Nara |
Nara Women's University |
Blind Separation of Sparse and Smooth Signals via Approximate Message Passing Algorithm Shigeki Yokoyama, Toshiyuki Tanaka (Kyoto Univ.) IBISML2013-76 |
We consider the problem to recover source signals from noisy mixed ones. This can be described as a matrix reconstructio... [more] |
IBISML2013-76 pp.71-78 |
IBISML |
2013-11-13 15:45 |
Tokyo |
Tokyo Institute of Technology, Kuramae-Kaikan |
[Poster Presentation]
Gaussian Sparse Hashing Koichiro Suzuki, Mitsuru Ambai, Ikuro Sato (Denso IT Labo) IBISML2013-56 |
Binary hashing has been widely used for Approximate Nearest Neighbor(ANN) search due to fast query
speed and less stora... [more] |
IBISML2013-56 pp.155-160 |
MBE, NC (Joint) |
2012-03-14 16:00 |
Tokyo |
Tamagawa University |
Incremental Learning for regression on a budget Koichiro Yamauchi (Chubu Univ) NC2011-145 |
In our previous work, we had proposed a limited general regression neural network (LGRNN) for embedded systems.
The LGR... [more] |
NC2011-145 pp.141-146 |
IBISML |
2012-03-13 15:40 |
Tokyo |
The Institute of Statistical Mathematics |
Improving Importance Estimation in Pool-based Batch Active Learning for Approximate Linear Regression Nozomi Kurihara, Masashi Sugiyama (Tokyo Inst. of Tech.) IBISML2011-105 |
Pool-based batch active learning is aimed at choosing training inputs from a `pool' of test inputs so that the generaliz... [more] |
IBISML2011-105 pp.123-130 |
NC, MBE (Joint) |
2011-03-07 11:30 |
Tokyo |
Tamagawa University |
Maximum Power Point Tracking Converter Using a Limited General Regression Neural Network Koichiro Yamauchi (Chubu Univ) NC2010-134 |
In this paper, we propose a limited general regression neural network (LGRNN) for embedded systems.
The LGRNN is an imp... [more] |
NC2010-134 pp.41-46 |
NC, MBE [detail] |
2010-12-19 11:45 |
Aichi |
Nagoya Univ. |
Limited General Regression Neural Networks Koichiro Yamauchi (Chubu Univ.) MBE2010-71 NC2010-82 |
An incremental learning method for the general regression neural network(GRNN) for embedded systems is proposed.
Althou... [more] |
MBE2010-71 NC2010-82 pp.91-96 |