===============================================
Technical Committee on Infomation-Based Induction Sciences and Machine Learning (IBISML)
Chair: Ichiro Takeuchi (Nagoya Inst. of Tech.)
Vice Chair: Masashi Sugiyama (Univ. of Tokyo), Koji Tsuda (Univ. of Tokyo)
Secretary: Toshihiro Kamishima (AIST), Tomoharu Iwata (NTT)
Assistant: Atsuyoshi Nakamura (Hokkaido Univ.), Shigeyuki Oba (Miidas)
DATE:
Tue, Mar 2, 2021 10:00 - 16:45
Wed, Mar 3, 2021 09:00 - 15:40
Thu, Mar 4, 2021 09:00 - 17:00
PLACE:
Online
TOPICS:
Organized and general sessions on machine learning
----------------------------------------
Tue, Mar 2 AM (10:00 - 11:40)
----------------------------------------
(1) 10:00 - 10:25
Learning from Noisy Complementary Labels with Robust Loss Functions
Hiroki Ishiguro (UTokyo), Takashi Ishida (UTokyo/RIKEN), Masashi Sugiyama (RIKEN/UTokyo)
(2) 10:25 - 10:50
Selective Inference for Convex Clustering Using Parametric Programming
Yumehiro Omori, Yu Inatsu (Nitech), Ichiro Takeuchi (Nitech/RIKEN)
(3) 10:50 - 11:15
Kernel tensor decomposition based unsupervised feature extraction
-- Applications to bioinformatics --
Y-h. Taguchi (Chuo Univ.)
(4) 11:15 - 11:40
Interdisciplinary Integration by Artificial Intelligence
-- Tasks of Discipline Science --
Kumon Tokumaru (Writer)
----------------------------------------
Tue, Mar 2 PM (13:00 - 16:45)
----------------------------------------
----- ( 5 min. ) -----
(5) 13:05 - 13:45
(See Japanese page.)
(6) 13:45 - 14:25
(See Japanese page.)
(7) 14:25 - 15:05
(See Japanese page.)
----- ( 15 min. ) -----
(8) 15:20 - 16:00
(See Japanese page.)
(9) 16:00 - 16:40
(See Japanese page.)
----- ( 5 min. ) -----
----------------------------------------
Wed, Mar 3 AM (09:00 - 12:40)
----------------------------------------
----- ( 5 min. ) -----
(10) 09:05 - 09:45
(See Japanese page.)
(11) 09:45 - 10:25
(See Japanese page.)
(12) 10:25 - 11:05
(See Japanese page.)
----- ( 10 min. ) -----
(13) 11:15 - 11:55
(See Japanese page.)
(14) 11:55 - 12:35
(See Japanese page.)
----- ( 5 min. ) -----
----------------------------------------
Wed, Mar 3 PM (14:00 - 15:40)
----------------------------------------
(15) 14:00 - 14:25
Learning coefficients of normal mixture models in one dimension.
Genki Watanabe, Ryuji Ito, Miki Aoyagi (Nihon Univ.)
(16) 14:25 - 14:50
Markov Decision Processes for Simultaneous Control of Multiple Objects with Different State Transition Probabilities in Each Cluster
Yuto Motomura, Akira Kamatsuka, Koki Kazama, Toshiyasu Matsushima (Waseda Univ.)
(17) 14:50 - 15:15
Safe reinforcement learning in high-dimensional continuous spaces
Takumi Umemoto (NIT), Tohgoroh Matsui (Chubu Univ.), Atsuko Mutoh, Koich Moriyama, Inuzuka Nobuhiro (NIT)
(18) 15:15 - 15:40
Selective Inference for Change-point Detection in Multi-dimensional Series Data
Ryota Sugiyama, Hiroki Toda, Vo Nguyen Le Duy, Yu Inatsu (NIT), Ichiro Takeuchi (NIT/RIKEN)
----------------------------------------
Thu, Mar 4 AM (09:00 - 12:40)
----------------------------------------
----- ( 5 min. ) -----
(19) 09:05 - 09:45
(See Japanese page.)
(20) 09:45 - 10:25
(See Japanese page.)
(21) 10:25 - 11:05
(See Japanese page.)
----- ( 10 min. ) -----
(22) 11:15 - 11:55
(See Japanese page.)
(23) 11:55 - 12:35
(See Japanese page.)
----- ( 5 min. ) -----
----------------------------------------
Thu, Mar 4 PM (13:15 - 17:00)
----------------------------------------
----- ( 5 min. ) -----
(24) 13:20 - 14:00
(See Japanese page.)
(25) 14:00 - 14:40
(See Japanese page.)
(26) 14:40 - 15:20
(See Japanese page.)
----- ( 15 min. ) -----
(27) 15:35 - 16:15
(See Japanese page.)
(28) 16:15 - 16:55
(See Japanese page.)
----- ( 5 min. ) -----
# 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:
Mon, Jun 28, 2021 - Wed, Jun 30, 2021: Online [Mon, May 10]
# SECRETARY:
Mahito Sugiyama (National Institute of Informatics) i
Last modified: 2021-03-03 16:30:37
|
Notification: Mail addresses are partially hidden against SPAM.
|