Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
IT |
2017-07-14 15:35 |
Chiba |
Chiba University |
Asymptotic Exponential Family of Markov Sources is Equivalent to Exponential Family of Markov Kernels Jun'ichi Takeuchi (Kyushu Univ.), Hiroshi Nagaoka (UEC) IT2017-36 |
For familes of Markov models, we prove that the notion of asymptotic exponential familly is equivalent to the notion of ... [more] |
IT2017-36 pp.115-119 |
IA, ICSS |
2017-06-09 10:30 |
Kochi |
Kochi University of Technolo, Eikokuji Campus |
[Invited Talk]
Applying AI for Cyber Security Jun'ichi Takeuchi (Kyushu Univ./NICT) |
[more] |
|
ISEC, WBS, IT |
2017-03-10 11:20 |
Tokyo |
TOKAI University |
MRI Acceleration by Super Resolution Ayaka Nakashima, Masanori Kawakita, Yutaka Jitsumatsu (Kyushu Univ.), Shigehide Kuhara (Kyorin Univ.), Jun'ichi Takeuchi (Kyushu Univ.) IT2016-124 ISEC2016-114 WBS2016-100 |
MR imaging currently takes a long imaging time in some applications such as 3D imaging and faster imaging speed is requi... [more] |
IT2016-124 ISEC2016-114 WBS2016-100 pp.161-166 |
IT, SIP, RCS |
2017-01-20 10:25 |
Osaka |
Osaka City Univ. |
A Study on Cardinality of Typical Set and High Probability Set Munenori Eto, Masanori Kawakita, Jun'ichi Takeuchi (Kyusyu Univ.) IT2016-87 SIP2016-125 RCS2016-277 |
[more] |
IT2016-87 SIP2016-125 RCS2016-277 pp.237-242 |
IT, SIP, RCS |
2017-01-20 10:50 |
Osaka |
Osaka City Univ. |
Decoding Algorithm of Sparse Superposition Codes (SSC) Yuwa Hatae, Kohei Miyamoto, Masanori Kawakita (Kyushu Univ.), Kazushi Mimura (Hiroshima City Univ.), Jun'ichi Takeuchi (Kyushu Univ.) IT2016-88 SIP2016-126 RCS2016-278 |
[more] |
IT2016-88 SIP2016-126 RCS2016-278 pp.243-248 |
RCS, IT, SIP |
2016-01-18 14:30 |
Osaka |
Kwansei Gakuin Univ. Osaka Umeda Campus |
An Improved Upper Bound on Block Error Probability of Least Squares Sparse Superposition Codes with Bernoulli Dictionary Yoshinari Takeishi, Jun'ichi Takeuchi (Kyshu Univ.) IT2015-66 SIP2015-80 RCS2015-298 |
[more] |
IT2015-66 SIP2015-80 RCS2015-298 pp.107-112 |
IT |
2015-07-13 15:15 |
Tokyo |
Tokyo Institute of Technology |
Design and Analysis of MDL Estimators for Supervised Learning Jun'ichi Takeuchi, Masanori Kawakita (Kyushu Univ.) IT2015-26 |
Barron and Coveys theory
to evaluate risk bounds for the MDL estimators (1991)
is basically for unsupervised learning... [more] |
IT2015-26 pp.53-58 |
NC, IPSJ-BIO, IBISML, IPSJ-MPS (Joint) [detail] |
2015-06-23 17:00 |
Okinawa |
Okinawa Institute of Science and Technology |
Risk Bound of Lasso Based on MDL Theory Masanori Kawakita, Yushin Toyokihara, Jun'ichi Takeuchi (Kyushu Univ.) IBISML2015-16 |
We derive a risk bound of lasso in random design linear regression. Past
works of MDL principle revealed that penalized... [more] |
IBISML2015-16 pp.101-107 |
ISEC, IT, WBS |
2015-03-03 11:20 |
Fukuoka |
The University of Kitakyushu |
Bonnet Detection Using Anomaly Detection Based on Sparse Structure Learning Shu Mukai, Yuki Kawamura, Masanori Kawakita, Jun'ichi Takeuchi (Kyushu Univ.) IT2014-92 ISEC2014-105 WBS2014-84 |
[more] |
IT2014-92 ISEC2014-105 WBS2014-84 pp.193-198 |
ISEC, IT, WBS |
2015-03-03 10:30 |
Fukuoka |
The University of Kitakyushu |
On Upper Bounds on Estimation Error of Least Squares Rgression with L1 Penalty Yushin Toyokihara, Masanori Kawakita, Jun'ichi Takeuchi (Kyushu Univ) IT2014-93 ISEC2014-106 WBS2014-85 |
In 1991, Barron and Cover showed for the MDL estimator that its estimation error is bounded by
codelength of the corres... [more] |
IT2014-93 ISEC2014-106 WBS2014-85 pp.199-204 |
IT |
2014-07-18 17:15 |
Hyogo |
Kobe University |
Geometry of Markov Chains, Finite State Machines, and Tree Models Jun'ichi Takeuchi (Kyushu Univ.) IT2014-40 |
[more] |
IT2014-40 pp.159-164 |
IT |
2014-05-16 15:40 |
Oita |
Beppu International Convention Center |
Performance Evaluation of Sparse Superposition Codes by Numerical Experiments Kohei Miyamoto, Misato Takaki, Masanori Kawakita, Jun'ichi Takeuchi (Kyushu Univ.) IT2014-10 |
[more] |
IT2014-10 pp.49-54 |
ICSS |
2013-11-12 15:50 |
Fukuoka |
Nishijin Plaza |
Experimental Evaluation of A Botnet Detection Method based on Non-negative Matrix Factorization Yuki Kawamura (Kyushu Univ.), Junpei Shimamura, Junji Nakazato (NICT), Katsunari Yoshioka (Yokohama National Univ.), Masashi Eto, Daisuke Inoue (NICT), Jun'ichi Takeuchi (Kyushu Univ.), Koji Nakao (NICT) ICSS2013-61 |
[more] |
ICSS2013-61 pp.23-28 |
IBISML |
2013-03-05 15:00 |
Aichi |
Nagoya Institute of Technology |
Evaluation of the limit performance of single frame super-resolution Masanori Kawakita, Kouratarou Yamaguchi, Norikazu Takahashi, Jun'ichi Takeuchi (Kyushu Univ.) IBISML2012-106 |
We elucidate the potential limit of single-frame super-resolution by
information theory. A single-frame super-resoluti... [more] |
IBISML2012-106 pp.95-100 |
IT |
2012-09-28 10:15 |
Gunma |
Kusatsu Seminar House |
Sparse Superposition Codes with Bernoulli Dictionary Yoshinari Takeishi, Masanori Kawakita, Jun'ichi Takeuchi (Kyushu Univ.) IT2012-38 |
We study some extension of the sparse superposition codes proposed by Barron and Joseph in 2010. The original sparse sup... [more] |
IT2012-38 pp.41-46 |
ICSS |
2012-03-16 14:10 |
Tokyo |
Kikai-Shinko-Kaikan Bldg. |
A Behavior-based Detection Method for Outbreaks of Low-rate Attacks Yaokai Feng, Yoshiaki Hori, Kouichi Sakurai, Jun'ichi Takeuchi (ISIT) ICSS2011-45 |
Low-rate attacks can conceal their traffic because they are very much like normal communication. Thus, although a number... [more] |
ICSS2011-45 pp.37-42 |
PRMU, IBISML, IPSJ-CVIM [detail] |
2011-09-05 10:30 |
Hokkaido |
|
On Evaluation of Stochastic Complexity based on Bayes Code and Its Applications to Model Selection Yoshinari Takeishi, Masanori Kawakita, Jun'ichi Takeuchi (Kyushu Univ./ISIT) PRMU2011-59 IBISML2011-18 |
We evaluate stochastic complexity of Gaussian mixture by Bayes code length, and apply it to the model selection problem.... [more] |
PRMU2011-59 IBISML2011-18 pp.9-14 |
PRMU, IBISML, IPSJ-CVIM [detail] |
2011-09-06 10:00 |
Hokkaido |
|
Acceleration of boosting discrimination and its application to face detection Ryota Izumi, Masanori Kawakita, Jun'ichi Takeuchi (kyushu Univ/ISIT), Hu Yi, Tetsuya Takamori, Hirokazu Kameyama (Fuji Film) PRMU2011-70 IBISML2011-29 |
We propose an acceleration technique for boosting classification.
Not only classification
accuracy and/or training cos... [more] |
PRMU2011-70 IBISML2011-29 pp.111-117 |
IBISML |
2011-06-20 16:45 |
Tokyo |
Takeda Hall |
Efficient Algorithms for Universal Portfolio defined by Markov Models Mariko Tsurusaki, Jun'ichi Takeuchi (Kyushu Univ.) IBISML2011-4 |
[more] |
IBISML2011-4 pp.21-28 |
CQ, MVE, IE (Joint) [detail] |
2011-03-07 15:00 |
Nagasaki |
Yasuragi IOUJIMA |
Estimation of location parameters using SIFT in image super-resolution Yoshitaka Kiyota, Daisuke Okumura, Masanori Kawakita, Norikazu Takahashi, Jun'ichi Takeuchi (ISIT/Kyushu Univ.) IE2010-168 MVE2010-156 |
[more] |
IE2010-168 MVE2010-156 pp.129-134 |