Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
IBISML |
2019-03-05 13:30 |
Tokyo |
RIKEN AIP |
A connection between Kida's optimal signal approximation and the signal classification by maximizing margin Takuro Kida (Tokyo Tech. Prof.EM), Yuichi Kida (Ohu Univ.) IBISML2018-105 |
[more] |
IBISML2018-105 pp.1-8 |
IBISML |
2019-03-05 14:00 |
Tokyo |
RIKEN AIP |
Expressive power of skip connection and network architecture Jumpei Nagase, Tetsuya Ishiwata (Shibaura Inst. of Tech.) IBISML2018-106 |
Model design is one of research topics in deep learning. Proposing a better model has been extensively studied, but ther... [more] |
IBISML2018-106 pp.9-15 |
IBISML |
2019-03-05 14:30 |
Tokyo |
RIKEN AIP |
Efficient Exploration by Variational Information Maximizing Exploration on Reinforcement Learning Kazuki Doi, Keigo Okawa (Gifu Univ.), Motoki Shiga (Gifu Univ./JST/RIKEN) IBISML2018-107 |
In reinforcement learning,the policy function may not be optimized properly if the observed state space is limited to lo... [more] |
IBISML2018-107 pp.17-22 |
IBISML |
2019-03-05 16:30 |
Tokyo |
RIKEN AIP |
Set transformer for coordinating outfits Takuma Nakamura, Yuki Saito (ZOZO Research) IBISML2018-108 |
We have evaluated Set Transformer, the permutation invariant neural network model, for selecting fashion items and gener... [more] |
IBISML2018-108 pp.23-29 |
IBISML |
2019-03-05 17:00 |
Tokyo |
RIKEN AIP |
A Study on Automatic Generation of False Data Injection Attack against Connected Car Service Based on Reinforcement Learning Yuichiro Dan, Keita Hasegawa, Takafumi Harada, Tomoaki Washio, Yoshihito Oshima (NTT) IBISML2018-109 |
While the connected car is predicted to prevail by 2025, the appearance of novel cyber attacks is concerned. In this pap... [more] |
IBISML2018-109 pp.31-38 |
IBISML |
2019-03-06 10:00 |
Tokyo |
RIKEN AIP |
Effects of Batch-normalization on Fisher Information Matrix of ResNet Yasutaka Furusho, Kazushi Ikeda (NAIST) IBISML2018-110 |
ResNet have intensively been studied and many techniques have been used for better performance.
Batch-normalization (BN... [more] |
IBISML2018-110 pp.39-44 |
IBISML |
2019-03-06 10:30 |
Tokyo |
RIKEN AIP |
Wider neural networks with ReLU activation generalize better Yasutaka Furusho, Kazushi Ikeda (NAIST) IBISML2018-111 |
Model size determination is important in machine learning since a larger model leads to overfitting, that is, a small tr... [more] |
IBISML2018-111 pp.45-50 |
IBISML |
2019-03-06 11:00 |
Tokyo |
RIKEN AIP |
Shapelet-based Multiple-Instance Learning Daiki Suehiro, Kohei Hatano (Kyushu Univ./RIKEN AIP), Eiji Takimoto (Kyushu Univ.), Shuji Yamamoto, Kenichi Bannai (Keio Univ./RIKEN AIP), Akiko Takeda (The Univ. of Tokyo/RIKEN AIP) IBISML2018-112 |
[more] |
IBISML2018-112 pp.51-58 |
IBISML |
2019-03-06 11:30 |
Tokyo |
RIKEN AIP |
Optimal Kernel for Mode Estimation via Kernel Density Estimation Ryoya Yamasaki, Toshiyuki Tanaka (Kyoto Univ.) IBISML2018-113 |
We have derived kernel functions that minimize the asymptotic mean squared error of the mode estimate, which is defined ... [more] |
IBISML2018-113 pp.59-64 |
IBISML |
2019-03-06 13:00 |
Tokyo |
RIKEN AIP |
Magnetic Resonance Angiography Image Restoration by Super Resolution based on Deep Learning Shizen Kitazaki, Masanori Kawakita, Yutaka Jitumatu (Kyushu Univ.), Shigehide Kuhara (Kyorin Univ.), Akio Hiwatashi, Jun'ichi Takeuchi (Kyushu Univ.) IBISML2018-114 |
Magnetic Resonance Imaging (MRI) is one of the powerful techniques to acquire in vivo information. However, to obtain a ... [more] |
IBISML2018-114 pp.65-72 |
IBISML |
2019-03-06 13:30 |
Tokyo |
RIKEN AIP |
Acceleration of Boosting Discriminators Using Region Partition Learning and Its Application to Face Detectors Takeshi Mori, Junichi Takeuchi, Masanori Kawakita (Kyushu Univ.) IBISML2018-115 |
We propose a method of acceleration of boosting discriminators.
Discriminant functions used for boosting are constructe... [more] |
IBISML2018-115 pp.73-80 |
IBISML |
2019-03-06 14:00 |
Tokyo |
RIKEN AIP |
Evaluation of LGRF using RAVE in Go program Tatsuya Shimizu, Yuta Hayama, Asuka Nakamura, Yoshitaka Maekawa (CIT) IBISML2018-116 |
This paper proposes an improving method of Monte Carlo tree search to improve the winning rate of the Go program. The p... [more] |
IBISML2018-116 pp.81-85 |