Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
NC, IPSJ-BIO, IBISML, IPSJ-MPS [detail] |
2017-06-23 16:00 |
Okinawa |
Okinawa Institute of Science and Technology |
Analysis of Robustness of Approximators Based on Neural Networks Against Redundant Dimensions Shoichi Someno, Tomohiro Tanno, Kazumasa Horie, Jun Izawa, Tomoki Ichiba, Masahiko Morita (Tsukuba Univ.) NC2017-8 |
Redundant input dimensions that are not related to the output are known to lower the approximate accuracy of function ap... [more] |
NC2017-8 pp.21-26 |
NC, IPSJ-BIO, IBISML, IPSJ-MPS [detail] |
2017-06-23 16:25 |
Okinawa |
Okinawa Institute of Science and Technology |
Analysis of Sequential Learning Capability of Selective Desensitization Neural Network Tomoki Ichiba, Tomohiro Tanno, Kazumasa Horie, Jun Izawa, Syoichi Someno, Masahiko Morita (Tsukuba Univ.) NC2017-9 |
A conventional neural network with high generalization ability is known to entirely forget the previously learned inform... [more] |
NC2017-9 pp.27-32 |
NC, IPSJ-BIO |
2013-06-28 15:10 |
Okinawa |
Okinawa Institute of Science and Technology |
Effect of Pattern Coding on Pattern Classification Neural Networks Tomohiro Tanno, Kazumasa Horie, Takaaki Kobayashi, Masahiko Morita (Univ. of Tsukuba) NC2013-13 |
Recent studies reported that the performance of layered neural networks to approximate multivariable functions improves ... [more] |
NC2013-13 pp.139-143 |
NC, IPSJ-BIO |
2012-06-28 10:10 |
Okinawa |
OIST, Okinawa |
Multi-Class EMG Pattern Classfication using a Selective Desensitization Neural Network with a Half-vs-Half Method Kazumasa Horie (Univ. of Tsukuba), Atsuo Suemitsu (JAIST), Masahiko Morita (Univ. of Tsukuba) NC2012-3 |
The real-time classication of human movements by using surface electromyogram (EMG) signals is an important research is... [more] |
NC2012-3 pp.13-18 |
NC, IPSJ-BIO |
2012-06-28 11:10 |
Okinawa |
OIST, Okinawa |
A Computational Model for State Value Estimation in the Brain Using Two Kinds of Temporal Differences Masanari Shinotsuka, Masahiko Morita (Univ. of Tsukuba) NC2012-5 |
The basal ganglia has been considered to be deeply involved in reinforcement learning since Schultz et al. reported that... [more] |
NC2012-5 pp.25-30 |
NC, IPSJ-BIO [detail] |
2011-06-24 14:15 |
Okinawa |
50th Anniversary Memorial Hall, University of the Ryukyus |
The Capability of Selective Desensitization Neural Networks at Two-Variable Function Approximation Kazuaki Nonaka, Fumihide Tanaka, Masahiko Morita (Tsukuba Univ) NC2011-14 |
Selective Desensitization Neural Network (SDNN) is known to be able to approximate some functions well with high general... [more] |
NC2011-14 pp.113-118 |
NC, IPSJ-BIO [detail] |
2011-06-24 14:40 |
Okinawa |
50th Anniversary Memorial Hall, University of the Ryukyus |
Q-learning in Continuous Action-State Space by Using a Selective Desensitization Neural Network Takaaki Kobayashi, Takeshi Shibuya, Fumihide Tanaka, Masahiko Morita (Tsukuba Univ) NC2011-15 |
Value function approximation takes an important role for reinforcement learning in continuous state-action space. Conven... [more] |
NC2011-15 pp.119-123 |
NC, NLP, IPSJ-BIO [detail] |
2010-06-18 15:35 |
Okinawa |
Ryukyu-daigaku-gozyu-syunen-kinenn-kaikan |
Discrimination of Hand Motion from Surface EMG Signals Using a Selective Desensitization Neural Network Hiroshi Kawata (Univ. of Tsukuba), Atsuo Suemitsu (JAIST), Masahiko Morita (Univ. of Tsukuba) NLP2010-6 NC2010-6 |
Real-time discrimination of hand motion from surface EMG signals is useful for developing surface EMG prosthetic arms, i... [more] |
NLP2010-6 NC2010-6 pp.37-44 |
HIP, HCS |
2010-05-14 13:30 |
Okinawa |
Okinawa Industry Support Center |
Estimation of the chunk structure in visuomotor procedural memory based on finger velocity Masanobu Sakata, Hiromi Morita, Masahiko Morita (Univ. of Tsukuba) HCS2010-18 HIP2010-18 |
Although the existence of "chunks" in procedural memory is suggested by the analysis of button-press intervals in a sequ... [more] |
HCS2010-18 HIP2010-18 pp.97-102 |
NC |
2009-01-19 10:55 |
Hokkaido |
Hokkaido Univ. |
Reinforcement Learning Using Selective Desensitization Neural Networks in the State Space with Redundant dimensions Tomoyuki Shimbo, Ken Yamane, Masahiko Morita (Univ. of Tsukuba) NC2008-83 |
Reinforcement learning has a problem that it requires a long time particularly when the state space is high dimensional ... [more] |
NC2008-83 pp.7-12 |
NC, MBE (Joint) |
2008-03-13 15:20 |
Tokyo |
Tamagawa Univ |
Efficiency improvement of reinforce learning using a selective desensitization neural network Masahiko Morita, Tomoyuki Shimbo, Takashi Hasuo, Ken Yamane (Univ. of Tsukuba) NC2007-172 |
Existing reinforcement learning (RL) systems have a serious problem that they require an extremely long time for learnin... [more] |
NC2007-172 pp.355-359 |
NC |
2007-03-15 15:50 |
Tokyo |
Tamagawa University |
Modeling the activity of the hippocampal neurons based on the theory of selective desensitization Yasuhiro Miyazawa (Univ. of Tsukuba), Atsuo Suemitsu (Shimane Univ.), Masahiko Morita (Univ. of Tsukuba) |
Integrating different kinds of information is thought to be a key function of the hippocampus.
Based on a computational... [more] |
NC2006-184 pp.183-188 |