Dear colleagues,
(日本語は下にあります)

We will hold a seminar by Dr. Jun Tani on 27 July, Tuesday.

Dr. Tani is a prominent researcher in the field of cognitive robotics,
study on  cognitive science with robotic systems.   I welcome everyone
who  are interested  in cognitive  science and  robotic  systems.

The seminar will be done in English.
                         ^^^^^^^^^^
Date:    27 July, Tuesday
Time:    13:30-15:00
Place:   K12 lecture room, Knowledge Science

Speaker: Dr. Jun Tani 
         Brain Science Institute, the Institute of Physical and
         Chemical Researches (RIKEN)

Title:   Cognitive Robotics Experiments Using a Mirror Neuron Model

Abstract:

My talk  reviews a connectionist  model, the recurrent  neural network
with parametric  biases (RNNPB),  in which multiple  behavior schemata
can be learned by the network in a distributed manner.  The parametric
biases in  the network play an  essential role in  both generating and
recognizing behavior patterns.   They act as a mirror  system by means
of self-organizing adequate  memory structures.  Three different robot
experiments  are  reviewed:  robot  and user  imitative  interactions;
learning  and  generating different  types  of  dynamic patterns;  and
linguistic-behavior binding.  The hallmark of this study is explaining
how   self-organizing   internal    structures   can   contribute   to
generalization in  learning, and diversity in  behavior generation, in
the proposed distributed representation  scheme.  The reference can be
seen at http://www.bdc.brain.riken.go.jp/~tani/



--------------------------------------------------------------
各位

来る7月27日(火) 午後1時30分より、知識K12講義室において、理研の谷淳氏に
よる研究室主催セミナーを開催いたします。

講師の谷淳氏は、認知ロボティクス(ロボットを用いた認知研究)の第一人者で
す。認知科学、ロボット等に興味をお持ちの方は、ぜひご来聴下さい。

なお、本講演は講義(複合システム特論)の一環であり、講演は英語で行われま
す。                                              

開催日：  2004年 7月27日 (火) 13:30〜15:00

場所：    知識 K1,2 講義室

講演者：  谷 淳 氏 (理化学研究所・脳科学総合研究センター)

講演題目：
   Cognitive Robotics Experiments Using a Mirror Neuron Model

概要：

My talk  reviews a connectionist  model, the recurrent  neural network
with parametric  biases (RNNPB),  in which multiple  behavior schemata
can be learned by the network in a distributed manner.  The parametric
biases in  the network play an  essential role in  both generating and
recognizing behavior patterns.   They act as a mirror  system by means
of self-organizing adequate  memory structures.  Three different robot
experiments  are  reviewed:  robot  and user  imitative  interactions;
learning  and  generating different  types  of  dynamic patterns;  and
linguistic-behavior binding.  The hallmark of this study is explaining
how   self-organizing   internal    structures   can   contribute   to
generalization in  learning, and diversity in  behavior generation, in
the proposed distributed representation  scheme.  The reference can be
seen at http://www.bdc.brain.riken.go.jp/~tani/