Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
IN, CCS (Joint) |
2022-08-04 14:00 |
Hokkaido |
Hokkaido University(Centennial Hall) (Primary: On-site, Secondary: Online) |
On Learning of MLP by PSO with Perturbation Riku Takatou, Kenya Jin'no (Tokyo City Univ.) CCS2022-32 |
Attempt to learn the coupling coefficients of a multiclass classifier using a simplified multilayer perceptron (MLP) wit... [more] |
CCS2022-32 pp.30-34 |
IN, IA (Joint) |
2021-12-17 14:30 |
Hiroshima |
Higashi-Senda campus, Hiroshima Univ. (Primary: On-site, Secondary: Online) |
Evaluating Prediction of the Access Counts of Videos Using Metadata as a Learning Parameter Gen Koujitani, Masaya Nakayama (Univ. Tokyo) IA2021-47 |
In order to predict the number of accesses to videos posted on video sharing services, we performed regression predictio... [more] |
IA2021-47 pp.77-84 |
VLD, DC, RECONF, ICD, IPSJ-SLDM (Joint) [detail] |
2021-12-01 10:10 |
Online |
Online |
A Multilayer Perceptron Training Accelerator using Systolic Array Takeshi Senoo, Akira Jinguji, Ryosuke Kuramochi, Hiroki Nakahara (Toyko Tech) VLD2021-23 ICD2021-33 DC2021-29 RECONF2021-31 |
Neural networks are being used in various applications, and the demand for fast training with large amounts of data is e... [more] |
VLD2021-23 ICD2021-33 DC2021-29 RECONF2021-31 pp.37-42 |
EA, SIP, SP |
2019-03-14 13:30 |
Nagasaki |
i+Land nagasaki (Nagasaki-shi) |
[Poster Presentation]
Snore sound identification using noise suppression and multi-class classification under real environments Keisuke Nishijima, Ken'ichi Furuya (Oita Univ.) EA2018-106 SIP2018-112 SP2018-68 |
In the conventional snore sound identification method, there is an issue that performance deteriorates when identifying ... [more] |
EA2018-106 SIP2018-112 SP2018-68 pp.43-48 |
ICSS |
2018-11-21 14:50 |
Kagoshima |
|
Spoofed Website Detection using Machine Learning Naoki Kurihara, Hidenori Tsuji, Masaki Hashimoto (Institute of Information Security) ICSS2018-56 |
In recent years, the damage by fake site has been rapidly increasing. Because fake sites are ceremonious as if they are ... [more] |
ICSS2018-56 pp.19-24 |
IMQ |
2018-10-19 15:05 |
Kyoto |
Kyoto Institute of Technology |
Examination of dimensionality of multilayer perceptron estimating dislocation regions in multicrystalline silicon photoluminescence image Hiroaki Kudo, Tetsuya Matsumoto (Nagoya Univ.), Kentaro Kutsukake (RIKEN), Noritaka Usami (Nagoya Univ.) IMQ2018-14 |
In this report, we studied a specified method of regions including dislocations which are crystallographic defects in a ... [more] |
IMQ2018-14 pp.19-24 |
SC |
2018-06-02 09:25 |
Fukushima |
UBIC 3D Theater, University of Aizu |
Simultaneous recognition of human activities and locations based on sensor array Shoichi Ichimura, Qiangfu Zhao (Univ. of Aizu) SC2018-11 |
In recent years, smart homes for senior care have attracted great attention in Japan. But a smart home has a privacy iss... [more] |
SC2018-11 pp.59-64 |
IBISML |
2017-11-10 13:00 |
Tokyo |
Univ. of Tokyo |
Analysis of Dropout in online learning Kazuyuki Hara (Nihon Univ.) IBISML2017-61 |
Deep learning is the state-of-the-art in fields such as visual object recognition and speech recognition.
This learning... [more] |
IBISML2017-61 pp.201-206 |
NLC, TL |
2016-06-04 16:50 |
Hokkaido |
Otaru University of Commerce |
Identification of Tweets that Mention Books
-- Effects of Features, Data Size, and ML Algorithms -- Shuntaro Yada, Kyo Kageura (UTokyo) TL2016-7 NLC2016-7 |
We report performances of a classifier that identify Tweets that Mention Books (TMB) from tweets that contain the same s... [more] |
TL2016-7 NLC2016-7 pp.29-34 |
NC, MBE |
2015-03-16 15:35 |
Tokyo |
Tamagawa University |
Further Speeding Up and Solution Quality Improvement of Singularity Stairs Following Seiya Satoh, Ryohei Nakano (Chubu Univ.) MBE2014-168 NC2014-119 |
In a search space of a multilayer perceptron (MLP), there exists singular regions where any point is I-O equivalent to t... [more] |
MBE2014-168 NC2014-119 pp.289-294 |
NC, MBE (Joint) |
2013-12-21 15:20 |
Gifu |
Gifu University |
Singularity Stairs Following with Limited Numbers of Hidden Units Seiya Satoh, Ryohei Nakano (Chubu Univ.) NC2013-65 |
In a search space of a multilayer perceptron having J hidden units, MLP(J), there exist flat areas called singular regio... [more] |
NC2013-65 pp.69-74 |
NC, NLP |
2013-01-24 09:30 |
Hokkaido |
Hokkaido University Centennial Memory Hall |
Multilayer Perceptron Search Making Good Use of Singular Regions Seiya Satoh, Ryohei Nakano (Chubu Univ.) NLP2012-104 NC2012-94 |
In a search space of multilayer perceptron having J hidden units, MLP(J), there exists a singular flat region created by... [more] |
NLP2012-104 NC2012-94 pp.1-6 |
NC, NLP |
2013-01-24 09:50 |
Hokkaido |
Hokkaido University Centennial Memory Hall |
Multilayer Perceptron Model Selection Using Sampling Utilizing Singularity Stairs Following Takayuki Ohwaki, Ryohei Nakano (Chubu Univ.) NLP2012-105 NC2012-95 |
Multilayer perceptron (MLP) is one of singular statistical models, where it is not guaranteed that any parameter is uniq... [more] |
NLP2012-105 NC2012-95 pp.7-12 |
SANE |
2012-01-26 13:00 |
Nagasaki |
Nagasaki Prefectural Art Museum |
Learning for ATC decision on priority of runway usage Masato Fujita (ENRI) SANE2011-141 |
With the miniaturization of aircraft and increasing air traffic demand, the workload of air traffic controllers is expec... [more] |
SANE2011-141 pp.1-4 |
NC, MBE (Joint) |
2011-12-20 11:20 |
Aichi |
Nagoya Institute of Technology |
Eigen Vector Descent and Line Search for Multilayer Perceptron Seiya Satoh, Ryohei Nakano (Chubu Univ.) NC2011-87 |
As learning methods of a multilayer perceptron (MLP), we have the BP algorithm, Newton's method, quasi-Newton method, an... [more] |
NC2011-87 pp.19-24 |
NC, MBE (Joint) |
2011-12-20 11:45 |
Aichi |
Nagoya Institute of Technology |
Complex-valued Multilayer Perceptron Search Unilizing Eigen Vector Descent and Reducibility Mapping Shinya Suzumura, Ryohei Nakano (Chubu Univ.) NC2011-88 |
A complex-valued multilayer perceptron (MLP) can approximate a periodic or unbounded function, which cannot be easily re... [more] |
NC2011-88 pp.25-30 |
SP |
2011-06-23 13:00 |
Aichi |
Nagoya Univ. |
[Invited Talk]
Fundamentals and recent research trends in feature extraction Takashi Fukuda (IBM) SP2011-30 |
Cepstral coefficients and their dynamics that represent temporal variations have been widely used for automatic speech r... [more] |
SP2011-30 pp.1-6 |
AN, MoNA, USN (Joint) |
2011-01-20 12:00 |
Hiroshima |
Hiroshima City University |
[Technology Exhibit]
Adaptive Estimation of Displayed Presence Messages using Personal Attributes Hiroshi Isomura, Yuusuke Kawakita (UEC), Miyuki Imada (NTT), Etsuko Suzuki, Haruhisa Ichikawa (UEC) MoMuC2010-64 AN2010-55 USN2010-48 |
Sensing one’s personal situation (presence) and showing it to others facilitates communication, but showing same presenc... [more] |
MoMuC2010-64 AN2010-55 USN2010-48 pp.29-30(MoMuC), pp.59-60(AN), pp.53-54(USN) |
NLP |
2008-11-06 10:50 |
Aichi |
|
Structure Extraction of Time Series Generated by Multiple Rules Junichiro Kotani, Yasukuni Mori, Ikuo Matsuba (Chiba Univ.) NLP2008-59 |
In time series analysis a structure of time series is often described by one rule.
However, sometimes time series may b... [more] |
NLP2008-59 pp.11-16 |
NC, MBE (Joint) |
2008-03-13 11:10 |
Tokyo |
Tamagawa Univ |
Handwritten Character Distinction Method Inspired by Human Vision Mechanism Junpei Koyama (The Univ. of Tokyo), Masahiro Kato (Fuji Xerox), Akira Hirose (The Univ. of Tokyo) NC2007-151 |
We deal with distinction between handwritten and machine-printed characters in document images. Current distinction tech... [more] |
NC2007-151 pp.231-236 |