Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
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 |
IBISML |
2013-11-13 15:45 |
Tokyo |
Tokyo Institute of Technology, Kuramae-Kaikan |
[Poster Presentation]
Infinite Positive Semidefinite Tensor Factorization based on Gamma Process for Music Signal Analysis Kazuyoshi Yoshii (AIST), Ryota Tomioka (Univ. of Tokyo), Daichi Mochihashi (ISM), Masataka Goto (AIST) IBISML2013-57 |
This paper presents positive semidefinite tensor factorization (PSDTF) that is a natural extension of nonnegative matrix... [more] |
IBISML2013-57 pp.161-168 |
IBISML |
2013-11-13 15:45 |
Tokyo |
Tokyo Institute of Technology, Kuramae-Kaikan |
[Poster Presentation]
Probabilistic Partial Canonical Correlation Analysis Yusuke Mukuta, Tatsuya Harada (Univ. of Tokyo) IBISML2013-58 |
Partial Canonical Correlation Analysis (Partial CCA) is a statistical method to estimate a pair of linear projections on... [more] |
IBISML2013-58 pp.169-176 |
IBISML |
2013-11-13 15:45 |
Tokyo |
Tokyo Institute of Technology, Kuramae-Kaikan |
[Poster Presentation]
Improvement of independent component analysis by an estimation of the error distribution of higher-order statistics Yoshitatsu Matsuda, Kazunori Yamaguchi (Univ. of Tokyo) IBISML2013-59 |
Independent component analysis (ICA) is a solution for blind source
separation problems.
ICA can estimate the source... [more] |
IBISML2013-59 pp.177-183 |
IBISML |
2013-11-13 15:45 |
Tokyo |
Tokyo Institute of Technology, Kuramae-Kaikan |
[Poster Presentation]
Energy Disaggregation for Appliance Loads Based on Semi-Supervised NMF Yu Fujimoto, Naoki Okubo, Yasuhiro Hayashi (Waseda Univ.), Yoshimasa Sugitate, Shiro Ogata (Omron) IBISML2013-60 |
The authors propose an application of non-negative matrix factorization for the energy disaggregation task. The method i... [more] |
IBISML2013-60 pp.185-190 |
IBISML |
2013-11-13 15:45 |
Tokyo |
Tokyo Institute of Technology, Kuramae-Kaikan |
[Poster Presentation]
Efficient Exhaustive Search for Variable Selection with Exchange Monte Carlo Method Kenji Nagata (Univ. of Tokyo), Jun Kitazono (JST), Shinichi Nakajima (Nikon), Satoshi Eifuku (Fukushima Medical Univ.), Ryoi Tamura (Univ. of Toyama), Masato Okada (Univ. of Tokyo) IBISML2013-61 |
[more] |
IBISML2013-61 pp.191-196 |
IBISML |
2013-11-13 15:45 |
Tokyo |
Tokyo Institute of Technology, Kuramae-Kaikan |
[Poster Presentation]
Floor-plan partitioning stochastic processes for relational data analysis Masahiro Nakano, Katsuhiko Ishiguro, Akisato Kimura, Takeshi Yamada, Naonori Ueda (NTT) IBISML2013-62 |
This paper presents a floor-plan partitioning stochastic process, that can potentially generate arbitrary rectangular pa... [more] |
IBISML2013-62 pp.197-204 |
IBISML |
2013-11-13 15:45 |
Tokyo |
Tokyo Institute of Technology, Kuramae-Kaikan |
[Poster Presentation]
Stochastic Dual Coordinate Ascent with Alternating Direction Multiplier Method Taiji Suzuki (Tokyo Inst. of Tech.) IBISML2013-63 |
We propose a new stochastic dual coordinate ascent technique
that can be applied to a wide range of regularized learni... [more] |
IBISML2013-63 pp.205-212 |
IBISML |
2013-11-13 15:45 |
Tokyo |
Tokyo Institute of Technology, Kuramae-Kaikan |
[Poster Presentation]
Safe Screening Rule for Incmrenetal Learning Yoshiki Suzuki, Shota Okumura, Kohei Ogawa, Ichiro Takeuchi (Nagoya Inst. of Tech.) IBISML2013-64 |
Efficient optimization algorithm is required in online learning or other incremental learning scenario since the model m... [more] |
IBISML2013-64 pp.213-218 |
IBISML |
2013-11-13 15:45 |
Tokyo |
Tokyo Institute of Technology, Kuramae-Kaikan |
[Poster Presentation]
Statistical-mechanical analysis of active noise control Rei Fujiwara, Yoshinobu Kajikawa, Seiji Miyoshi (Kansai Univ.) IBISML2013-65 |
We analyze the dynamical behaviors (learning curves) of
the active noise control using a statistical-method.
Cross-co... [more] |
IBISML2013-65 pp.219-224 |
IBISML |
2013-11-13 15:45 |
Tokyo |
Tokyo Institute of Technology, Kuramae-Kaikan |
[Poster Presentation]
Learning Common Features of Parametrized Tasks Ichiro Takeuchi, Tatsuya Hongo (Nagoya Inst. of Tech.), Masashi Sugiyama (Tokyo Inst. of Tech.), Shinichi Nakajima (Nikon) IBISML2013-66 |
We introduce a novel formulation of multi-task learning (MTL) called parametric task learning (PTL) that can systematica... [more] |
IBISML2013-66 pp.225-232 |