Hiroshi Yamakawa's Home Page

---

Research

1. Publication list(Abstracts)
2. Research theme
• Situation decomposition using Matchability criterion
• Cognition based Intelligent Transaction Architecture (CITTA) - Agent network -
• Contract on Learning oriented Multiagent System [Paper/Poster]
• Research on Real World Adaptable Autonomous Systems - Development of a Hand-to-HandRobot[Paper]
• Autoencoder neural network
• Sensor based robot arm system
• Creative intelligence (future work)
• Intelligent System based on ReinforcementLearning(Doctoral Thesis(1992),Japanese)[PDF/PDF+ZIP]
• Intelligent System with Sense of Values
• Active State Control on Recurrent Neural Network
• Neural System Navigating in Maze World
3. 　RWC Related work

Bibliography

• Mar. 1987: Received a B.S. degree in physics from the Faculty of Scince division, Science University of Tokyo (Takahashi Lab. : now Suzuki Lab.)
• Mar. 1989: Received a M.S. degree in physics from the University of Tokyo (Kakizaki Lab.) Master thesis: "Ultraviolet photo electron spectroscopy for liquid metal"
• Mar. 1992: Received a Dr. Engineering degree in electronics from University of Tokyo (Okabe Lab.） Doctor thesis: "Intelligent system based on reinforcement learning"
• Apr. 1992 - Sept. 1994: Fujitsu Laboratories Ltd.
1. Sensor fusion (Japanese national project)
2. Hierarchical sensor information processing model
3. Active Data Selection and Subsequent Revision for Sequential Learning with Neural Networks
4. Unsupervised Acquisition of Hierarchical Internal Representation with Autoencoder Neural Networks
• Oct. 1994 - : Tukuba research center, Real world computing partnership
• Apr. 1997 - : Return to Fujitsu Laboratories Ltd.

Hobby

• Ski:
• Tennis:
• Basket ball:
• In-line skate: