TITLE: On Performance Skill Representation Framework

PRESENTER: Professor Koichi Furukawa, http://vu.sfc.keio.ac.jp/faculty/profile.cgi?1+furukawa, furukawa@sfc.keio.ac.jp

AFFILIATION:Graduate School of Media and Governance, Keio University, Japan, http://bruch.sfc.keio.ac.jp

DATE: Wednesday 15th March 2006

TIME: 12:00:00

PLACE: CSE Seminar Room, Level 1, K17

ABSTRACT:

In this talk, we propose a framework for representing performance
skill. Firstly, we notice the importance of performance skill
representation. We introduce five different representation targets:
performance tasks, performance rules, pre-shaping actions, dynamic
integrity constraints, and performance states. Performance task
description consists of a sequence of performance tasks and
expressions. It acts as a goal description in planning. Performance
rules describe model performance methods for given tasks including how
to shape body parts and how to use various muscles. Pre-shaping
action rules are similar to performance rules. Its role is to
pre-shape in between consecutive tasks to prepare for the next task.
Dynamic integrity constraints specify constraints to be satisfied
during performance. It also is related to a fundamental research
issue of attributes finding/selection in discovering useful rules for
skillful performance.

BIOGRAPHY OF SPEAKER:

Koichi Furukawa (Professor, Graduate School of Media and Governance,
Keio University) graduated from the Graduate School of Engineering,
Tokyo University in 1967. He entered the Electrotechnical Laboratory
in 1967 and joined ICOT, the Japanese Fifth Generation Computer Project,
in 1985. He was deputy director of the project from 1986 to 1991.
Prof. Furukawa moved to Keio University in 1992. His area of interest
is Machine Learning, particularly Inductive Logic Programming and Skill Science.

Host:

Claude Sammut

Seminar Convenor:

Van Hai Ho