Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
COMP |
2013-09-03 10:45 |
Tottori |
|
A New UCB-based Algorithm for the Matching-Selection Multi-armed Bandit Problem Ryo Watanabe, Atsuyoshi Nakamura, Mineichi Kudo (Hokkaido Univ.) COMP2013-26 |
Permutation bandit problem is a kind of combinatorial multi-armed bandit problem in which an $M$-permutation of $N$ elem... [more] |
COMP2013-26 pp.9-16 |
IBISML |
2013-03-04 14:15 |
Aichi |
Nagoya Institute of Technology |
Passive-Aggressive Algorithm with Bias Daigo Tateishi, Kohei Hatano, Eiji Takimoto (Kyushu Univ.) IBISML2012-93 |
We consider online binary classication problems by using linear classiers. Among online learning
algorithms for linea... [more] |
IBISML2012-93 pp.1-8 |
IBISML |
2012-06-19 11:00 |
Kyoto |
Campus plaza Kyoto |
Online Prediction under Submodular Constraints Daiki Suehiro, Kohei Hatano, Shuji Kijima, Eiji Takimoto (Kyushu Univ.), Kiyohito Nagano (Tokyo Univ.) IBISML2012-3 |
[more] |
IBISML2012-3 pp.15-22 |
CAS, CS, SIP |
2012-03-08 14:10 |
Niigata |
The University of Niigata |
Three variants of alternating direction method of multipliers without certain inner iterations and their application to image super-resolution via sparse representation Masao Yamagishi, Shunsuke Ono, Isao Yamada (Tokyo Inst. of Tech.) CAS2011-115 SIP2011-135 CS2011-107 |
We propose three variants of Alternating Direction Method of Multipliers (ADMM) employing simplified updates under addit... [more] |
CAS2011-115 SIP2011-135 CS2011-107 pp.49-54 |
NLP |
2011-11-09 16:20 |
Okinawa |
Miyako Island Marine Terminal |
Robust Training of the Feedforward Neural Networks using hybrid quasi-Newton Training Algorithm Toshikazu Abe, Yoshihiko Sakashita, Hiroshi Ninomiya (SIT) NLP2011-105 |
Various techniques based on the gradient descent method have been studied as training algorithms for neuralnetworks. Neu... [more] |
NLP2011-105 pp.75-80 |
PRMU, IBISML, IPSJ-CVIM [detail] |
2011-09-05 15:20 |
Hokkaido |
|
Feature Selection for Object Tracking based on Online Real Boosting Takayoshi Yamashita (Omron), Hironobu Fujiyoshi (Chubu University.) PRMU2011-68 IBISML2011-27 |
Recently, Boosting algorithms like AdaBoost and Real AdaBoost are used in online learning. The weak classifiers for onli... [more] |
PRMU2011-68 IBISML2011-27 pp.67-73 |
EA |
2011-06-23 14:00 |
Hokkaido |
Health Sci. Univ. of Hokkaido |
Improvement of Noise Reduction Performance of ANC Systems with Online Secondary Path Modeling Technique using Two Secondary Path Models Akihisa Oishi, Muhammad Tahir Akhtar, Wataru Mitsuhashi (UEC) EA2011-31 |
A new technique is proposed for a controlled injection of the noise to model the secondary acoustic path in the feedforw... [more] |
EA2011-31 pp.7-12 |
RCS |
2011-04-22 11:10 |
Kanagawa |
Keio University |
Impact of the Channel Feedback Load Reduction on Performance of Downlink Linear and Nonlinear Multiuser MIMO Satoshi Sonobe, Yafei Hou, Kazuto Yano, Masahiro Uno, Masazumi Ueba (ATR) RCS2011-12 |
In this paper, on downlink multiuser MIMO-OFDM system, we evalute the impact of reducing the number of subaband on the p... [more] |
RCS2011-12 pp.65-70 |
NC, NLP |
2011-01-24 09:30 |
Hokkaido |
Hokakido Univ. |
Parameterized online quasi-Newton Training Algorithm for Feedforward Neural Networks Hiroshi Ninomiya (SIT) NLP2010-125 NC2010-89 |
This paper describes a new gradient based technique for training of feedforward neural networks. Recently, improved onli... [more] |
NLP2010-125 NC2010-89 pp.1-6 |
COMP |
2010-12-03 16:00 |
Fukuoka |
Kyutech Plaza, Kyushu Institute of Technology |
Improving the Competitive Ratios of the Seat Reservation Problem Kazuya Okamoto, Shuichi Miyazaki (Kyoto Univ.) COMP2010-45 |
In the seat reservation problem, there are $k$ stations, $s_{1}$
through $s_{k}$, and one train with $n$ seats departin... [more] |
COMP2010-45 pp.45-51 |
NC, NLP, IPSJ-BIO [detail] |
2010-06-18 16:50 |
Okinawa |
Ryukyu-daigaku-gozyu-syunen-kinenn-kaikan |
Study on Robust Training of Neural Networks using Gradient-based Algorithm with Improved Feeding-technique of Training Data Toshikazu Abe, Yoshihiko Sakashita, Hiroshi Ninomiya (Shonan Inst. of Tech.) NLP2010-9 NC2010-9 |
Various techniques based on the gradient descent method have been studied as the training algorithm for neural networks.... [more] |
NLP2010-9 NC2010-9 pp.57-62 |
COMP |
2010-03-12 15:50 |
Tokyo |
National Institute of Informatics |
Online graph exploration algorithms for cycles and trees by multiple number of searchers Yuya Higashikawa, Naoki Katoh, Shin-ichi Tanigawa (Kyoto Univ.), Stefan Langerman (ULB) COMP2009-57 |
This paper deals with online graph exploration problems by multiple searchers. The purpose of search is to visit all ver... [more] |
COMP2009-57 pp.49-56 |
COMP |
2010-01-25 09:30 |
Fukuoka |
Nishijin Plaza, Kyushu University |
Competitive Analysis of the k-Canadian Traveller Problem for Graphs with Restricted Edge Weights Takeshi Fukuda, Shuichi Miyazaki, Yasuo Okabe (Kyoto Univ.) COMP2009-39 |
The $k$-Canadian Traveller Problem ($k$-CTP) is one of the online problems.
In this problem, we are given an undirected... [more] |
COMP2009-39 pp.1-8 |
SAT |
2009-10-29 13:20 |
Nara |
Nara Prefectural New Public Hall |
Experimental Test of Frequency Reuse Interference Canceller in the Path Containing Nonlinear TWTA Kenta Kubo, Hiroki Matsuda, Kayoko Osawa (NAIST), Taro Shimada, Shigeo Naoi, Yozo Takeda (SKY perfectJSAT), Ryusuke Miyamoto, Takao Hara, Minoru Okada (NAIST) SAT2009-22 |
The interference canceller for satellite carrier superpositioning
multi-level PSK transmission has been designed and
d... [more] |
SAT2009-22 pp.23-28 |
NC, MBE (Joint) |
2009-03-11 13:55 |
Tokyo |
Tamagawa Univ. |
Estimation of Intracellular Calcium Ion Concentration by Non-Linear State Space Modeling Takamasa Tsunoda (Tokyo Inst. of Tech.), Toshiaki Omori (univ. of tokyo/RIKEN Brain Sci Inst.), Hiroyoshi Miyakawa (Tokyo Univ. of Phar and Life Sci.), Masato Okada (univ. of tokyo/RIKEN Brain Sci Inst.), Toru Aonishi (Tokyo Inst. of Tech./RIKEN Brain Sci Inst.) NC2008-107 |
The ionic dynamics depending on the nervous activity recently attracts attentions of many researchers due to the rapid p... [more] |
NC2008-107 pp.25-30 |
COMP |
2008-03-10 16:45 |
Kanagawa |
|
Multiplicative Weight Update Algorithm for Metrical Task Systems Shingo Kawabata, Eiji Takimoto (Tohoku Univ.) COMP2007-66 |
Multiplicative weight update algorithms work very well for various online prediction problems.
We apply the method to a... [more] |
COMP2007-66 pp.75-82 |
NC |
2007-03-15 11:40 |
Tokyo |
Tamagawa University |
Speculative variable selection methods for quick online learning of classification tasks Shinpei Masuda, Youhei Tadeuchi, Kyosuke Nishida, Koichiro Yamauchi (Hokkaido Univ.) |
Generally, high dimensional datasets usually include redundant or useless features to achieve the learning of specified ... [more] |
NC2006-175 pp.129-134 |
PRMU, HIP |
2007-02-22 16:15 |
Kanagawa |
|
Online Action Recognition with Structured Boosting Yu Nejigane, Masamichi Shimosaka, Taketoshi Mori, Tomomasa Sato (Tokyo Univ.) |
In this paper, we propose a robust online action recognition method based on boosted sequential classification. Our meth... [more] |
PRMU2006-216 HIP2006-109 pp.59-64 |
NLP, CAS |
2006-10-04 14:05 |
Osaka |
|
A SPICE-Oriented Method for Finding DC Operating Points of Nonlinear Circuits Containing Piecewise-Linear Macromodels Wataru Kuroki, Kiyotaka Yamamura (Chuo Univ.) |
Recently, efficient algorithms have been proposed for finding all characteristic curves of one-port piecewise-linear (PW... [more] |
CAS2006-25 NLP2006-48 pp.25-30 |
SANE |
2006-04-11 15:50 |
Overseas |
Xidian Univ., Xi'an, China |
Adaptive Narrowband Interference Suppression in DSSS Yong-jun Sun, Ke-chu Yi, Xin Su (Xidian Univ.) SANE2006-41 |
The paper proposes ways to estimate whether narrowband interferences(NBIs) exist in DSSS or not. Through estimation diff... [more] |
SANE2006-41 pp.225-230 |