Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
IBISML |
2012-11-07 15:30 |
Tokyo |
Bunkyo School Building, Tokyo Campus, Tsukuba Univ. |
Stochastic policy gradient method for a stochastic policy using a Gaussian process regression Yutaka Nakamura, Hiroshi Ishiguro (Osaka Univ.) IBISML2012-52 |
Reinforcement learning (RL) methods using Gaussian process regression (GP) for approximating the value function have bee... [more] |
IBISML2012-52 pp.129-133 |
IBISML |
2012-11-07 15:30 |
Tokyo |
Bunkyo School Building, Tokyo Campus, Tsukuba Univ. |
Fast Gaussian Process Regression using hash function Yuya Okadome, Yutaka Nakamura, Hiroshi Ishiguro (Osaka Univ.) IBISML2012-55 |
A Gaussian Process Regression (GPR) has ability to deal with a non-linear regression easily.
However, the calculation c... [more] |
IBISML2012-55 pp.151-155 |
CNR |
2012-10-12 10:00 |
Okinawa |
OIST (Okinawa) |
Building a human-like conversational android based on large amount of chat data Toshiaki Nishio, Yuichiro Yoshikawa, Yutaka Nakamura (Osaka Univ), Hiroshi Ishiguro (Osaka Univ/ATR), Rollo Carpenter (Existor) CNR2012-10 |
To build a robot that interacts with humans in human-like ways, it should be provided with a capability of verbal commun... [more] |
CNR2012-10 pp.27-32 |
NC, MBE (Joint) |
2011-12-20 16:35 |
Aichi |
Nagoya Institute of Technology |
Flexible physical interaction based on control of the stiffness ellipse at the end effector by a musculoskeletal robotic arm
-- An application of an electromagnetic linear actuator -- Yoshihiro Nakata, Atsuhiro Ide, Yutaka Nakamura, Katsuhiro Hirata, Hiroshi Ishiguro (Osaka Univ.) NC2011-96 |
Development of mechanisms for robots in daily life to realize safe human-robot interaction is important issue of robotic... [more] |
NC2011-96 pp.69-74 |
IN, IA (Joint) |
2011-12-16 15:10 |
Hiroshima |
Hiroshima City University |
SSH Brute Force Attack Detection based on Flow Features Analysis Akihiro Satoh, Yutaka Nakamura, Takeshi Ikenaga (KIT) IN2011-119 |
SSH brute force attack has become more seriously, so administrators are desired to implement its countermeasures. In the... [more] |
IN2011-119 pp.73-78 |
IA, SITE, IPSJ-IOT [detail] |
2011-03-01 15:25 |
Kochi |
Kochi City Culture-Plaza CUL-PORT (Kochi prefecture) |
Scan Detection Method Based on Multi-Point Observation Kei Higashijima, Daiki Nobayashi, Yutaka Nakamura, Takeshi Ikenaga (KIT), Shunji Abe, Shigeo Urushidani, Shigeki Yamada (NII) SITE2010-66 IA2010-102 |
The Internet is important infrastructure of the social foundation.
The attacks to the Internet which obstruct stable op... [more] |
SITE2010-66 IA2010-102 pp.225-230 |
NC, MBE (Joint) |
2008-03-13 14:10 |
Tokyo |
Tamagawa Univ |
Policy gradient method for a policy function with probabilistic parameters Yutaka Nakamura (Osaka Univ.) NC2007-170 |
Stochastic policy gradient methods are a type of reinforcement learning method, where the parameter of the policy parame... [more] |
NC2007-170 pp.343-348 |
NS, IN (Joint) |
2008-03-06 10:10 |
Okinawa |
Bankoku Shinryokan |
Collaborated Link Evaluation with Packet Transfer Ratio in Multihop Wireless Network Daiki Nobayashi, Yutaka Nakamura, Takeshi Ikenaga (KIT), Yoshiaki Hori (Kyushu Univ.), Hiroshi Ishinishi (NAL), Shuuji Kaizaki (KEPC) IN2007-175 |
Multihop Wireless Network provides flexible network architecture to be enable adding one or more Access Points (APs) to ... [more] |
IN2007-175 pp.97-102 |
NS, IN (Joint) |
2008-03-07 13:30 |
Okinawa |
Bankoku Shinryokan |
Evaluation model of anomaly traffic detection mechanism with distributed sensors and its performance analysis Takefumi Kobayashi, Katsuyoshi Iida (Tokyo Tech), Yutaka Nakamura, Takeshi Ikenaga (Kyushu Tech) NS2007-194 |
There expands the damage caused by computer infections such as worms on
the Internet so that its countermeasure must be... [more] |
NS2007-194 pp.347-352 |
NS, CS, IN (Joint) |
2007-09-20 13:30 |
Miyagi |
Tohoku University |
Access Point Evaluation with Packet Transfer Ratio in Multihop Wireless Network Daiki Nobayashi, Yutaka Nakamura, Takeshi Ikenaga (KIT), Yoshiaki Hori (KU), Hiroshi Ishinishi (NAL) IN2007-49 |
Wireless LAN has been deployed widely to provide inexpensive access network for end systems. Especially Multiop Wireles... [more] |
IN2007-49 pp.37-42 |
NC |
2007-03-14 16:40 |
Tokyo |
Tamagawa University |
Learning of a robust controller for a biped robot based on sample reuse reinforcement learning method Tsuyoshi Ueno (NAIST), Yutaka Nakamura, Takashi Takuma (Osaka Univ.), Tomohiro Shibata (NAIST), Koh Hosoda (Osaka Univ.), Shin Ishii (NAIST) |
[more] |
NC2006-151 pp.197-202 |
NC |
2007-03-14 17:00 |
Tokyo |
Tamagawa University |
Acquiring vermicular motion of a Looper-like robot based on the CPG-Actor-Critic method Kenji Makino (NAIST), Yutaka Nakamura (Osaka Univ.), Tomohiro Shibata, Shin Ishii (NAIST) |
Adaptability to the environment is crucial for mobile robots, because the circumstance, including the body of the robot,... [more] |
NC2006-152 pp.203-208 |
NC |
2006-06-16 09:40 |
Okinawa |
OIST |
Feature Extraction for Decision-Theoretic Planning in Partially Observable Environments Hajime Fujita, Yutaka Nakamura, Shin Ishii (NAIST) |
We propose a feature extraction technique for decision-theoretic planning problems in partially observable stochastic do... [more] |
NC2006-24 pp.13-18 |
IA |
2006-05-24 11:15 |
Kyoto |
Campus Plaza Kyoto |
Development of Single Sign-On System with hardware token and key management server Daiki Nobayashi, Yutaka Nakamura, Takeshi Ikenaga (KIT) IA2006-2 |
With the growth of the Internet, various types of services,such as World Wide Web (WWW), File Transfer Protocol (FTP), r... [more] |
IA2006-2 pp.7-12 |
NC |
2006-03-17 11:00 |
Tokyo |
Tamagawa University |
Considering model error when applying an reinforcement learning method to control of a real robot Yoichi Tokita, Yutaka Nakamura (NAIST), Junichiro Yoshimoto (OIST), Shin Ishii (NAIST) |
Because reinforcement learning (RL) methods have an advantage such that a control rule can be obtained autonomously with... [more] |
NC2005-154 pp.19-24 |