IEICE Technical Committee Submission System
Advance Program
Online Proceedings
[Sign in]
Tech. Rep. Archives
 Go Top  Go Back   Prev IBISML Conf / Next IBISML Conf [HTML] / [HTML(simple)] / [TEXT]  [Japanese] / [English] 

===============================================
Technical Committee on Infomation-Based Induction Sciences and Machine Learning (IBISML)
Chair: Hisashi Kashima (Kyoto Univ.)
Vice Chair: Masashi Sugiyama (Univ. of Tokyo), Koji Tsuda (Univ. of Tokyo)
Secretary: Ichiro Takeuchi (Nagoya Inst. of Tech.), Toshihiro Kamishima (AIST)
Assistant: Tomoharu Iwata (NTT), Shigeyuki Oba (Kyoto Univ.)

DATE:
Thu, Jan 9, 2020 13:00 - 17:35
Fri, Jan 10, 2020 11:00 - 14:30

PLACE:
The Institute of Statistical Mathematics(10-3, Midori-cho, Tachikawa-shi, 190-8562 Japan.https://www.ism.ac.jp/access/index_e.html. ISM, Hideitsu Hino)

TOPICS:
Machine learning, etc.

----------------------------------------
Thu, Jan 9 PM Machine Learning (13:00 - 14:40)
----------------------------------------

(1) 13:00 - 13:25
Asymptotic Behavior of Bayesian Generalization Error in Multinomial Mixtures
Takumi Watanabe, Sumio Watanabe (Tokyo Tech)

(2) 13:25 - 13:50
Real Log Canonical Threshold of Three Layered Neural Network with Swish Activation Function
Raiki Tanaka, Sumio Watanabe (Tokyo Tech)

(3) 13:50 - 14:15
Dimensionality reduction method for gaussian process posteriors based on information geometry
Hideaki Ishibashi (Kyutech), Shotaro Akaho (AIST/RIKEN)

(4) 14:15 - 14:40
Statistical Learning Theory of Data changed in Value
Satoshi Kataoka (Titech)

----------------------------------------
Thu, Jan 9 PM Machine Learning (14:55 - 17:35)
----------------------------------------

(5) 14:55 - 15:20
Approximation Ratios of Graph Neural Networks for Combinatorial Problems
Ryoma Sato, Makoto Yamada, Hisashi Kashima (Kyoto Univ.)

(6) 15:20 - 15:45
Robust recovery of highly corrupted low-rank matrix via augmented Lagrangian multiplier
Tuersunjiang Yimamu, Toshio Eisaka (Kitami Inst. of Tech.)

(7) 15:45 - 16:10
(See Japanese page.)

----- Break ( 10 min. ) -----

(8) 16:20 - 16:45
Evaluation of effective degree of freedom of physical model by learning capacity
Yoh-ichi Mototake (ISM), Kenji Nagata (NIMS)

(9) 16:45 - 17:10
Application of tensor decomposition based unsupervised feature extraction to single cell RNA-seq analysis
Y-h. Taguchi (Chuo Univ.)

(10) 17:10 - 17:35
An Implementation of Artificial General Intelligence based on motion information extracted from video
Kenichi Koike

----------------------------------------
Fri, Jan 10 AM Machine Learning (11:00 - 11:50)
----------------------------------------

(11) 11:00 - 11:25
Hybrid authentication model using handwritten images by Siamese Network and dynamic information
Daisuke Hayashi, Taisuke Kawamata, Toru Kano, Takako Akakura (TUS)

(12) 11:25 - 11:50
Real-time 3D localization of multifocal plane microscopy using deep neural network
Toshimitsu Aritake (Waseda Univ.), Hideitsu Hino (ISM), Shigeyuki Namiki, Daisuke Asanuma, Kenzo Hirose (The Univ. of Tokyo), Noboru Murata (Waseda Univ.)

----------------------------------------
Fri, Jan 10 PM Machine Learning (13:15 - 14:30)
----------------------------------------

(13) 13:15 - 13:40
A Change Detection Method based on Temporal Variation of Subspace Geometry
Honami Kanamori, Naoya Sogi, Kazuhiro Fukui (Univ. Tsukuba)

(14) 13:40 - 14:05
Non-compensatory Temporal IRT with Local Variational Approximation
Hiroshi Tamano (NEC/SOKENDAI), Daichi Mochihashi (ISM)

(15) 14:05 - 14:30
Active learning for multiple data selection using reinforcement learning
Yuusuke Taguchi (Univ. of Tsukuba), Hideitsu Hino (ISM), Keisuke Kameyama (Univ. of Tsukuba)

# Information for speakers
General Talk will have 20 minutes for presentation and 5 minutes for discussion.


=== Technical Committee on Infomation-Based Induction Sciences and Machine Learning (IBISML) ===
# FUTURE SCHEDULE:

Jan, 2020: [unfixed]
Tue, Mar 10, 2020 - Wed, Mar 11, 2020: Kyoto University [Fri, Jan 17], Topics: Machine learning, etc.


Last modified: 2019-11-18 09:31:54


Notification: Mail addresses are partially hidden against SPAM.

[Download Paper's Information (in Japanese)] <-- Press download button after click here.
 
[Cover and Index of IEICE Technical Report by Issue]
 

[Presentation and Participation FAQ] (in Japanese)
 

[Return to IBISML Schedule Page]   /  
 
 Go Top  Go Back   Prev IBISML Conf / Next IBISML Conf [HTML] / [HTML(simple)] / [TEXT]  [Japanese] / [English] 


[Return to Top Page]

[Return to IEICE Web Page]


The Institute of Electronics, Information and Communication Engineers (IEICE), Japan