===============================================
Technical Committee on Infomation-Based Induction Sciences and Machine Learning (IBISML)
Chair: Kenji Fukumizu (ISM)
Vice Chair: Masashi Sugiyama (Univ. of Tokyo), Hisashi Kashima (Kyoto Univ.)
Secretary: Ichiro Takeuchi (Nagoya Inst. of Tech.), Koji Tsuda (Univ. of Tokyo)
Assistant: Tomoharu Iwata (NTT), Toshihiro Kamishima (AIST)
DATE:
Wed, Nov 8, 2017
Thu, Nov 9, 2017 13:00 - 15:30
Fri, Nov 10, 2017 13:00 - 15:30
PLACE:
Hongo Campus, Univ. of Tokyo(7-chome, Hongo, Bunkyo-ku, Tokyo, 113-8654 Japan. http://www.u-tokyo.ac.jp/en/about/access.html)
TOPICS:
Information-Based Induction Science Workshop (IBIS2017)
----------------------------------------
Thu, Nov 9 PM (13:00 - 15:30)
----------------------------------------
(1) 13:00 - 15:30
(See Japanese page.)
(2) 13:00 - 15:30
[Poster Presentation]
Extraction of Distribtion Changes using On-line t-SNE
Daisuke Kaji (Denso), Masahiro Kobayashi, Kazuho Watanabe (Toyohashi Tech.)
(3) 13:00 - 15:30
Calculation method for grid-structured markov random field using corner transfer matrix renormalization group
Tomoharu Yoshida, Kazuho Watanabe, Kyoji Umemura (Toyohashi Univ. of Tech.)
(4) 13:00 - 15:30
[Poster Presentation]
Real Log Canonical Threshold of Stochastic Matrix Factorization and its Application to Bayesian Learning
Naoki Hayashi, Sumio Watanabe (TokyoTech)
(5) 13:00 - 15:30
[Poster Presentation]
Empirical Bayesian Tree
Masashi Sekino (SMN)
(6) 13:00 - 15:30
Semi-Supervised AUC Optimization based on Positive-Unlabeled Learning
Tomoya Sakai, Gang Niu (UTokyo/RIKEN), Masashi Sugiyama (RIKEN/UTokyo)
(7) 13:00 - 15:30
Application of Transfer Learning to Smallscale Data and Its Evaluation Using Open Datasets
Arika Fukushima, Toru Yano, Shuuichiro Imahara, Hideyuki Aisu (Toshiba)
(8) 13:00 - 15:30
[Poster Presentation]
Evaluation of Machine Learning Methods for Anomaly Detection Using New Kyoto2006+ Dataset
Hisashi Takahara (UNP)
(9) 13:00 - 15:30
[Poster Presentation]
Material search for Li-ion battery electrolytes by exhaustive search with Gaussian Process modeling
Tomofumi Nakayama (Univ. Tokyo), Yasuhiko Igarashi, Keitaro Sodeyama (NIMS), Masato Okada (Univ. Tokyo)
(10) 13:00 - 15:30
[Poster Presentation]
Post Clustering Inference for Heterogeneous Data
Shigenori Inoue, Yuta Umezu (NIT), Shoma Tsubota (Nagoya Univ.), Ichiro Takeuchi (NIT/RIKEN/NIMS)
(11) 13:00 - 15:30
Robust one dimensional phase unwrapping using Markov random fields
Yasuhisa Nakashima (Univ. Tokyo), Yasuhiko Igarashi (JST), Yasushi Naruse (NICT), Masato Okada (Univ. Tokyo)
(12) 13:00 - 15:30
Regression Method for Noisy Inputs based on Naradaya-Watson Estimator constructed from Noiseless Training Data
Ryo Hanafusa, Takeshi Okadome (Kwansei Gakuin Univ.)
(13) 13:00 - 15:30
Online Optimization Method for Generalized $ell_1$ Regularized Problems
Yoshihiro Nakazato, Kazuto Fukuchi (Tsukuba Univ.), Jun Sakuma (Tsukuba Univ./Riken/JST)
(14) 13:00 - 15:30
(See Japanese page.)
(15) 13:00 - 15:30
Hidden Semi-Markov Model Representing State Overlap for Multiple Sequential Data Input
Hiromi Narimatsu, Hiroyuki Kasai (UEC)
(16) 13:00 - 15:30
Quantum inspired Machine Learning through Entanglement Entropy
Masaru Tanaka (Fukuoka UNiv.)
(17) 13:00 - 15:30
Nonconvex Sparse Optimization with Submodularity
Naoki Marumo, Tomoharu Iwata (NTT)
(18) 13:00 - 15:30
Regularization of learning prameters in posterior mean estimate approximation in CS-SENSE method
Ken Harada, Masato Inoue (Waseda Univ.), Kaori Togashi (Kyoto Univ.)
(19) 13:00 - 15:30
Consequently Fair Contextual Bandit Learning
Kazuto Fukuchi (Univ. of Tsukuba), Jun Sakuma (Univ. of Tsukuba/JST/RIKEN)
(20) 13:00 - 15:30
(See Japanese page.)
(21) 13:00 - 15:30
Evaluation of KL-divergence between Gaussian process posteriors by finite dimensional normal distributions
Hideaki Ishibashi, Tetsuo Furukawa (Kyutech), Shotaro Akaho (AIST)
(22) 13:00 - 15:30
Clinical Decision Support System based on Co-occurrence Analysis of Disease Names
-- Utilization of Clinical Big Text Data by Artificial Intelligence --
Ken Yano, Eiji Aramaki (NAIST)
(23) 13:00 - 15:30
Efficient modal regression using gradient ascent and descent method
Ryoya Yamasaki, Toshiyuki Tanaka (Kyoto Univ.)
(24) 13:00 - 15:30
[Poster Presentation]
Learning huge Bayesian networks using RAI algorithm based on Bayes factor
Kazuki Natori, Masaki Uto, Maomi Ueno (UEC)
(25) 13:00 - 15:30
Bayesian nonparametric model for uncountable factor analysis
Masahiro Nakano (NTT), Daichi Mochihashi, Tomoko Matsui (ISM), Kunio Kashino (NTT)
(26) 13:00 - 15:30
Fast Computation of Lower Bounds for Privacy Evaluations, Based on Binary Decision Diagrams
Shogo Takeuchi (Univ. of Tokyo), Kosuke Kusano, Jun Sakuma (Univ. of Tsukuba), Koji Tsuda (Univ. of Tokyo)
(27) 13:00 - 15:30
(See Japanese page.)
----------------------------------------
Fri, Nov 10 PM (13:00 - 15:30)
----------------------------------------
(28) 13:00 - 15:30
Analysis of Dropout in online learning
Kazuyuki Hara (Nihon Univ.)
(29) 13:00 - 15:30
[Poster Presentation]
Binary Classification from Positive-Confidence Data
Takashi Ishida (SMAM/UTokyo/RIKEN), Gang Niu (UTokyo/RIKEN), Masashi Sugiyama (RIKEN/UTokyo)
(30) 13:00 - 15:30
Rotated Image Recognition by Continuous execution of Angle Estimation Using a Feature Map with CNN
Nishiki Katayama, Satoshi Yamane (Kanazawa Univ.)
(31) 13:00 - 15:30
Safe Screening for Large Margin Metric Learning
Tomoki Yoshida (NITech), Ichiro Takeuchi (NITech/NIMS/RIKEN), Masayuki Karasuyama (NITech/NIMS/JST)
(32) 13:00 - 15:30
Convolutional Neural Network with Entanglement Entropy
Shu Eguchi, Masaru Tanaka (Fukuoka Univ.)
(33) 13:00 - 15:30
[Poster Presentation]
Multi-Task Learning with Positive and Unlabeled Data and Its Application to Mental State Prediction
Hirotaka Kaji, Hayato Yamaguchi (Toyota Motor), Masashi Sugiyama (RIKEN/UTokyo)
(34) 13:00 - 15:30
Hierarchical Reinforcement Learning Based on Return-Weighted Density Estimation
Takayuki Osa (UTokyo/RIKEN), Masashi Sugiyama (RIKEN/UTokyo)
(35) 13:00 - 15:30
[Poster Presentation]
Improvement of learning method with convolutional restricted Boltzmann machine based on PCD
Ryosuke Ishi, Reiki Suda, Koujin Takeda (Ibaraki Univ.)
(36) 13:00 - 15:30
[Poster Presentation]
Bin width optimization of multidimensional histogram on count data
Kensuke Muto, Hirotaka Sakamoto, Keisuke Matsuura, Takahisa Arima, Masato Okada (Tokyo Univ.)
(37) 13:00 - 15:30
[Poster Presentation]
Nonlinear parametric model based on power law for tsunami height prediction
Masashi Yoshikawa (UT), Yasuhiko Igarashi (JST), Shin Murata (UT), Toshitaka Baba (TU), Takane Hori (JAMSTEC), Masato Okada (UT)
(38) 13:00 - 15:30
[Poster Presentation]
Selective Inference for Change Point Detection in Multidimensional Sequence
Yuta Umezu (Nitech), Ichiro Takeuchi (Nitech/RIKEN/NIMS)
(39) 13:00 - 15:30
Compressed Sensing CT image reconstruction using Bayesian Optimization for mixing multiple image priors
Tomonori Suga, Masato Inoue (Waseda Univ.)
(40) 13:00 - 15:30
[Poster Presentation]
Correcting selection bias in active learning based on selective inference framework
Yu Inatsu (RIKEN), Ichiro Takeuchi (Nitech/RIKEN/NIMS)
(41) 13:00 - 15:30
[Poster Presentation]
Variational Bayes method for matrix factorization to two sparse factorized matrices
Tomoki Tamai, Koujin Takeda (Ibaraki Univ.)
(42) 13:00 - 15:30
Estimation of Training Data Distribution from Probabilistic Classifier using Generative Adversarial Networks
Kosuke Kusano, Jun Sakuma (Univ. Tsukuba)
(43) 13:00 - 15:30
A solution to the inverse Ising problem in tree-reweighted approximation
Takashi Sano (AIST)
(44) 13:00 - 15:30
Feature Extraction Using Empirical Mode Decomposition for Tire Sensing
Keita Ishii, Takato Goto (BS), Matsui Tomoko (ISM), Gareth Peters (HW), Nourddine Azzaoui (UCA)
(45) 13:00 - 15:30
[Poster Presentation]
Nearest Neighbor-based Anomaly Detection using Generative Adversarial Networks
Yoshiyuki Tajima (Hitachi)
(46) 13:00 - 15:30
[Poster Presentation]
Proposal of λ-scan Method in Spectral Deconvolution
Yohachi Mototake (Univ of Tokyo), Yasuhiko Igarashi (NIMS), Hikaru Takenaka (Univ of Tokyo), Kenji Nagata (AIST), Masato Okada (Univ of Tokyo)
(47) 13:00 - 15:30
Approximated hyperparameter distribution estimation using Gaussian process and Bayesian optimization
Shun Katakami, Hirotaka Sakamoto, Masato Okada (UTokyo)
(48) 13:00 - 15:30
Good Arm Identification via Bandit Feedback
Hideaki Kano, Junya Honda (UTokyo/RIKEN), Kentaro Sakamaki (UTokyo), Kentaro Matsuura (Johnson & Johnson), Atsuyoshi Nakamura (HU), Masashi Sugiyama (RIKEN/UTokyo)
(49) 13:00 - 15:30
Statistical Mechanical Analysis of Learning with Two-Layer Perceptron with Multiple Output Units
-- Reconsidering Plateau Phenomenon --
Yuki Yoshida (UTokyo), Ryo Karakida (AIST), Masato Okada (UTokyo/AIST/RIKEN BSI), Shun-ichi Amari (RIKEN BSI)
(50) 13:00 - 15:30
Active Learning based on Submodular Optimization Considering Label Expansion
Masanari Kimura, Kei Wakabayashi (Tsukuba Univ.)
(51) 13:00 - 15:30
(See Japanese page.)
(52) 13:00 - 15:30
[Poster Presentation]
Effect of maximum likelihood estimation after L1 regularization in learning of log-linear models
Kazuya Takabatake, Shotaro Akaho (AIST)
(53) 13:00 - 15:30
The Classification Problem in Generalized Label Noise Model
Tota Suko, Shunsuke Horii (Waseda Univ)
(54) 13:00 - 15:30
[Poster Presentation]
Structure Learning of Graph Product Multilayer Network-shaped Gaussian Markov Random Fields
Yuya Takashina, Masato Inoue (Waseda Univ.)
(55) 13:00 - 15:30
[Poster Presentation]
Learning Algorithm in Molecular Adaptation
Nobuyuki Takahashi (Hokkaido Univ. of Education, Hakodate)
# Information for speakers
Poster Presentation will have 150 minutes for presentation.
=== Technical Committee on Infomation-Based Induction Sciences and Machine Learning (IBISML) ===
Last modified: 2017-10-24 21:04:46
|
Notification: Mail addresses are partially hidden against SPAM.
|