| 2009 |
|---|
| 71 | EE | Kohei Hayashi,
Junichiro Hirayama,
Shin Ishii:
Dynamic Exponential Family Matrix Factorization.
PAKDD 2009: 452-462 |
| 2008 |
|---|
| 70 | EE | Yu Hiei,
Takeshi Mori,
Shin Ishii:
Self-organized Reinforcement Learning Based on Policy Gradient in Nonstationary Environments.
ICANN (1) 2008: 367-376 |
| 69 | EE | Yuki Taniguchi,
Takeshi Mori,
Shin Ishii:
A Continuous Internal-State Controller for Partially Observable Markov Decision Processes.
ICANN (1) 2008: 397-406 |
| 68 | EE | Tsuyoshi Ueno,
Motoaki Kawanabe,
Takeshi Mori,
Shin-ichi Maeda,
Shin Ishii:
A semiparametric statistical approach to model-free policy evaluation.
ICML 2008: 1072-1079 |
| 2007 |
|---|
| 67 | EE | Satoshi Osaga,
Junichiro Hirayama,
Takashi Takenouchi,
Shin Ishii:
A Probabilistic Model of MOSAIC.
FOCI 2007: 41-46 |
| 66 | EE | Takashi Takenouchi,
Shin Ishii:
Multiclass classification as a decoding problem.
FOCI 2007: 470-475 |
| 65 | EE | Yuki Taniguchi,
Takeshi Mori,
Shin Ishii:
Reinforcement Learning for Cooperative Actions in a Partially Observable Multi-agent System.
ICANN (1) 2007: 229-238 |
| 64 | EE | Atsunori Kanemura,
Shin-ichi Maeda,
Shin Ishii:
Edge-Preserving Bayesian Image Superresolution Based on Compound Markov Random Fields.
ICANN (2) 2007: 611-620 |
| 63 | EE | Tomohiro Shibata,
Takashi Bando,
Shin Ishii:
Visual Tracking Achieved by Adaptive Sampling from Hierarchical and Parallel Predictions.
ICONIP (1) 2007: 604-613 |
| 62 | EE | Shin-ichi Maeda,
Shin Ishii:
Optimization of Parametric Companding Function for an Efficient Coding.
ICONIP (1) 2007: 713-722 |
| 61 | EE | Junichiro Hirayama,
Masashi Nakatomi,
Takashi Takenouchi,
Shin Ishii:
Bayesian Collaborative Predictors for General User Modeling Tasks.
ICONIP (1) 2007: 742-751 |
| 60 | EE | Yuki Tsukada,
Yuichi Sakumura,
Shin Ishii:
Quantitative Morphodynamic Analysis of Time-Lapse Imaging by Edge Evolution Tracking.
ICONIP (2) 2007: 817-826 |
| 59 | EE | Takashi Takenouchi,
Shin Ishii:
A probabilistic decoding approach to multi-class classification.
IJCNN 2007: 2671-2676 |
| 58 | EE | Mizuki Ihara,
Shin-ichi Maeda,
Shin Ishii:
Estimation of the Source-Filter Model Using Temporal Dynamics.
IJCNN 2007: 3098-3103 |
| 57 | EE | Shigeyuki Oba,
Motoaki Kawanabe,
Klaus-Robert Müller,
Shin Ishii:
Heterogeneous Component Analysis.
NIPS 2007 |
| 56 | EE | Junichiro Hirayama,
Shin-ichi Maeda,
Shin Ishii:
Markov and Semi-Markov Switching of Source Appearances for Nonstationary Independent Component Analysis.
IEEE Transactions on Neural Networks 18(5): 1326-1342 (2007) |
| 55 | EE | Hajime Fujita,
Shin Ishii:
Model-Based Reinforcement Learning for Partially Observable Games with Sampling-Based State Estimation.
Neural Computation 19(11): 3051-3087 (2007) |
| 54 | EE | Yutaka Nakamura,
Takeshi Mori,
Masa-aki Sato,
Shin Ishii:
Reinforcement learning for a biped robot based on a CPG-actor-critic method.
Neural Networks 20(6): 723-735 (2007) |
| 2006 |
|---|
| 53 | EE | Hajime Fujita,
Yutaka Nakamura,
Shin Ishii:
Feature Extraction for Decision-Theoretic Planning in Partially Observable Environments.
ICANN (1) 2006: 820-829 |
| 52 | EE | Shigeyuki Oba,
Shin Ishii:
Semi-supervised Significance Score of Differential Gene Expressions.
ICANN (2) 2006: 808-817 |
| 51 | EE | Tsuyoshi Ueno,
Yutaka Nakamura,
Takashi Takuma,
Tomohiro Shibata,
Koh Hosoda,
Shin Ishii:
Fast and Stable Learning of Quasi-Passive Dynamic Walking by an Unstable Biped Robot based on Off-Policy Natural Actor-Critic.
IROS 2006: 5226-5231 |
| 50 | EE | Yuichi Sakumura,
Shin Ishii:
Stochastic resonance with differential code in feedforward network with intra-layer random connections.
Neural Networks 19(4): 469-476 (2006) |
| 49 | EE | Yasunobu Igarashi,
Yuichi Sakumura,
Shin Ishii:
The role of short-term depression in sustained neural activity in the prefrontal cortex: A simulation study.
Neural Networks 19(8): 1137-1152 (2006) |
| 48 | EE | Junichiro Hirayama,
Junichiro Yoshimoto,
Shin Ishii:
Balancing plasticity and stability of on-line learning based on hierarchical Bayesian adaptation of forgetting factors.
Neurocomputing 69(16-18): 1954-1961 (2006) |
| 47 | EE | Shin Ishii,
Wako Yoshida:
Reinforcement Learning: Machine Learning and Natural Learning.
New Generation Comput. 24(3): (2006) |
| 46 | EE | Takashi Bando,
Tomohiro Shibata,
Kenji Doya,
Shin Ishii:
Switching particle filters for efficient visual tracking.
Robotics and Autonomous Systems 54(10): 873-884 (2006) |
| 45 | EE | Kentarou Hitomi,
Tomohiro Shibata,
Yutaka Nakamura,
Shin Ishii:
Reinforcement learning for quasi-passive dynamic walking of an unstable biped robot.
Robotics and Autonomous Systems 54(12): 982-988 (2006) |
| 2005 |
|---|
| 44 | EE | Shigeyuki Oba,
Kikuya Kato,
Shin Ishii:
Multi-Scale Clustering for Gene Expression Profiling Data.
BIBE 2005: 210-217 |
| 43 | EE | Hajime Fujita,
Shin Ishii:
Model-based reinforcement learning for a multi-player card game with partial observability.
IAT 2005: 467-470 |
| 42 | EE | Naoto Yukinawa,
Shigeyuki Oba,
Kikuya Kato,
Shin Ishii:
Multi-class Pattern Classification Based on a Probabilistic Model of Combining Binary Classifiers.
ICANN (2) 2005: 337-342 |
| 41 | EE | Yutaka Nakamura,
Takeshi Mori,
Shin Ishii:
An Off-Policy Natural Policy Gradient Method for a Partial Observable Markov Decision Process.
ICANN (2) 2005: 431-436 |
| 40 | EE | Shin Ishii,
Hajime Fujita,
Masaoki Mitsutake,
Tatsuya Yamazaki,
Jun Matsuda,
Yoichiro Matsuno:
A Reinforcement Learning Scheme for a Partially-Observable Multi-Agent Game.
Machine Learning 59(1-2): 31-54 (2005) |
| 39 | EE | Shin-ichi Maeda,
Wen-Jie Song,
Shin Ishii:
Nonlinear and Noisy Extension of Independent Component Analysis: Theory and Its Application to a Pitch Sensation Model.
Neural Computation 17(1): 115-144 (2005) |
| 38 | EE | Wako Yoshida,
Shin Ishii:
Model-based reinforcement learning: a computational model and an fMRI study.
Neurocomputing 63: 253-269 (2005) |
| 2004 |
|---|
| 37 | | Takeshi Mori,
Yutaka Nakamura,
Masa-aki Sato,
Shin Ishii:
Reinforcement Learning for CPG-Driven Biped Robot.
AAAI 2004: 623-630 |
| 36 | EE | Takashi Bando,
Tomohiro Shibata,
Kenji Doya,
Shin Ishii:
Switching Particle Filters for Efficient Real-time Visual Tracking.
ICPR (2) 2004: 720-723 |
| 35 | EE | Yutaka Nakamura,
Takeshi Mori,
Shin Ishii:
Natural Policy Gradient Reinforcement Learning for a CPG Control of a Biped Robot.
PPSN 2004: 972-981 |
| 34 | EE | Shuichi Fukunaga,
Yutaka Nakamura,
Kazuaki Aso,
Shin Ishii:
Reinforcement learning for a snake-like robot controlled by a central pattern generator.
RAM 2004: 909-914 |
| 33 | EE | Junichiro Hirayama,
Junichiro Yoshimoto,
Shin Ishii:
Bayesian representation learning in the cortex regulated by acetylcholine.
Neural Networks 17(10): 1391-1400 (2004) |
| 32 | EE | Ken-ichi Amemori,
Shin Ishii:
Self-organization of delay lines by spike-time-dependent learning.
Neurocomputing 61: 291-316 (2004) |
| 31 | EE | Yasunori Ishihara,
Shin Ishii,
Hiroyuki Seki,
Minoru Ito:
Temporal Reasoning about Two Concurrent Sequences of Events.
SIAM J. Comput. 34(2): 498-513 (2004) |
| 2003 |
|---|
| 30 | EE | Wako Yoshida,
Shin Ishii:
A model-based reinforcement learning: a computational model and an fMRI study.
ESANN 2003: 313-318 |
| 29 | EE | Junichiro Yoshimoto,
Shin Ishii,
Masa-aki Sato:
System Identification Based on Online Variational Bayes Method and Its Application to Reinforcement Learning.
ICANN 2003: 123-131 |
| 28 | EE | Shigeyuki Oba,
Masa-aki Sato,
Shin Ishii:
Prior Hyperparameters in Bayesian PCA.
ICANN 2003: 271-279 |
| 27 | | Shigeyuki Oba,
Masa-aki Sato,
Ichiro Takemasa,
Morito Monden,
Ken-ichi Matsubara,
Shin Ishii:
A Bayesian missing value estimation method for gene expression profile data.
Bioinformatics 19(16): 2088-2096 (2003) |
| 26 | EE | Shigeyuki Oba,
Masa-aki Sato,
Shin Ishii:
Variational Bayes method for Mixture of Principal Component Analyzers.
Systems and Computers in Japan 34(11): 55-66 (2003) |
| 2002 |
|---|
| 25 | EE | Shigeyuki Oba,
Masa-aki Sato,
Ichiro Takemasa,
Morito Monden,
Ken-ichi Matsubara,
Shin Ishii:
Missing Value Estimation Using Mixture of PCAs.
ICANN 2002: 492-497 |
| 24 | EE | Taku Yoshioka,
Ryouko Morioka,
Kazuo Kobayashi,
Shigeyuki Oba,
Naotake Ogasawara,
Shin Ishii:
Clustering of Gene Expression Data by Mixture of PCA Models.
ICANN 2002: 522-527 |
| 23 | EE | Junichiro Yoshimoto,
Shin Ishii,
Masa-aki Sato:
Hierarchical Model Selection for NGnet Based on Variational Bayes Inference.
ICANN 2002: 661-666 |
| 22 | EE | Masa-aki Sato,
Yutaka Nakamura,
Shin Ishii:
Reinforcement Learning for Biped Locomotion.
ICANN 2002: 777-782 |
| 21 | EE | Shin Ishii,
Wako Yoshida,
Junichiro Yoshimoto:
Control of exploitation-exploration meta-parameter in reinforcement learning.
Neural Networks 15(4-6): 665-687 (2002) |
| 20 | EE | Shin Ishii,
Masa-aki Sato:
Doubly constrained network for combinatorial optimization.
Neurocomputing 43(1-4): 239-257 (2002) |
| 19 | EE | Yoichiro Matsuno,
Tatsuya Yamazaki,
Jun Matsuda,
Shin Ishii:
A multiagent reinforcement learning method based on the model inference of the other agents.
Systems and Computers in Japan 33(12): 67-76 (2002) |
| 2001 |
|---|
| 18 | EE | Yoichiro Matsuno,
Tatsuya Yamazaki,
Shin Ishii:
A multi-agent reinforcement learning method for a partially-observable competitive game.
Agents 2001: 39-40 |
| 17 | EE | Ken-ichi Amemori,
Shin Ishii:
Resonance of a Stochastic Spiking Neuron Mimicking the Hodgkin-Huxley Model.
ICANN 2001: 1087-1094 |
| 16 | EE | Shigeyuki Oba,
Masa-aki Sato,
Shin Ishii:
On-Line Learning Methods for Gaussian Processes.
ICANN 2001: 292-299 |
| 15 | EE | Ken-ichi Amemori,
Shin Ishii:
Gaussian Process Approach to Stochastic Spiking Neurons with Reset.
ICANN 2001: 361-368 |
| 14 | EE | Ken-ichi Amemori,
Shin Ishii:
Gaussian Process Approach to Spiking Neurons for Inhomogeneous Poisson Inputs.
Neural Computation 13(12): 2763-2797 (2001) |
| 13 | EE | Shin Ishii,
Masa-aki Sato:
Reconstruction of chaotic dynamics by on-line EM algorithm.
Neural Networks 14(9): 1239-1256 (2001) |
| 12 | EE | Junichiro Yoshimoto,
Shin Ishii,
Masa-aki Sato:
Application of reinforcement learning based on on-line EM algorithm to balancing of acrobot.
Systems and Computers in Japan 32(5): 12-20 (2001) |
| 2000 |
|---|
| 11 | EE | Yasuo Nagayuki,
Shin Ishii,
Kenji Doya:
Multi-Agent Reinforcement Learning: An Approach Based on the Other Agent's Internal Model.
ICMAS 2000: 215-221 |
| 10 | EE | Junichiro Yoshimoto,
Shin Ishii,
Masa-aki Sato:
On-Line EM Reinforcement Learning.
IJCNN (3) 2000: 163-168 |
| 9 | | Masa-aki Sato,
Shin Ishii:
On-line EM Algorithm for the Normalized Gaussian Network.
Neural Computation 12(2): 407-432 (2000) |
| 8 | | Shin Ishii,
Hirotaka Niitsuma:
-Opt Neural Approaches to Quadratic Assignment Problems.
Neural Computation 12(9): 2209-2225 (2000) |
| 7 | EE | Hirotaka Niitsuma,
Shin Ishii,
Minoru Ito:
Analog lambda-opt approach to quadratic assignment problem.
Systems and Computers in Japan 31(10): 1-9 (2000) |
| 1998 |
|---|
| 6 | | Ken-ichi Amemori,
Shin Ishii:
Self-Organizing Network Learning of Sub-Millisecond Temporal Coded Information.
ICONIP 1998: 1285-1288 |
| 5 | | Masa-aki Sato,
Shin Ishii:
On-Line EM Algorithm for Mixture of Local Experts.
ICONIP 1998: 1397-1401 |
| 4 | | Taku Yoshioka,
Shin Ishii,
Minoru Ito:
Strategy Acquisition for the Game "Othello" Based on Reinforcement Learning.
ICONIP 1998: 841-844 |
| 3 | EE | Masa-aki Sato,
Shin Ishii:
Reinforcement Learning Based on On-Line EM Algorithm.
NIPS 1998: 1052-1058 |
| 2 | EE | Shin Ishii,
Masa-aki Sato:
Constrained neural approaches to quadratic assignment problems.
Neural Networks 11(6): 1073-1082 (1998) |
| 1997 |
|---|
| 1 | EE | Shin Ishii,
Masa-aki Sato:
Chaotic Potts Spin Model for Combinatorial Optimization Problems.
Neural Networks 10(5): 941-963 (1997) |
