Untitled Document


뇌과학연구센터 세미나 개최

주제 : A Comparative Nonlinear Methodology for the Analysis of Biochemical Systems
발표자 : Micheal A. Savageau (Distinguished Professor, Univ.of California at Davis)

일자 : 2005년 02월 24일(목) 오후 5:00-6:00
장소 : KAIST 정문술빌딩 220호

뇌과학연구센터 세미나 개최

일시 : 2005년 2월 18일(금) 오후 1:00-2:30
장소 : KAIST 정문술빌딩 219호

Compositionality and Grounding:  A Dynamical Systems View through Neuro-Cognitive Robotics Experiments

Jun Tani
(Lab Head, Lab. for Behavior and Dynamic Cognition, RIKEN Brain Science Institute)

One of the crucial questions in building cognitive agents is how compositionality can be achieved in agents’ internal representations or memory structures, which are naturally grounded in sensory-motor competences. In conventional approaches, symbol systems allocated in a higher level are interfaced with lower level sensory-motor systems by employing certain categorizers.
These approaches, however, are likely to face the symbol grounding problem because the symbol and sensory-motor systems cannot share the same metric space.  Thus, their interfaces become arbitrary.  
We have proposed a dynamical systems approach using the “recurrent neural network with parametric biases” (RNNPB) as an alternative. The RNNPB can be characterized by its basic schema, which includes the following:  (1) a distributed representation of multiple behavioral schemas in a single network; (2) the ability to both generate and recognize sensory-motor flow as in a “mirror system”; (3) extension to hierarchical organization of behavioral schemas with chunking; (4) binding among multiple modalities.
My talk will review some of our robot behavior-learning experiments, including human imitation learning with using Sony humanoid robot as well as learning simple language and behavioral binding. Those experiments show that certain compositional structures hidden in word sequences, as well as experienced sensory-motor flow, are embedded in the self-organized dynamical structures of the RNNPB.  Furthermore, it has been observed that such "symbol systems", embedded in neuronal dynamical systems, can be naturally integrated with sensory-motor competences since they share the same metric space.  I will discuss the implications of this study as well as perspectives on future research.

뇌과학연구센터 세미나 개최

주제 : Reconfiguable networks of spiking neurons and plastic synapse
발표자 : Dr. Giacomo Indiveri (ETH Zurich)

일자 : 2005년 01월 18일(화) 오후 2:30-4:00
장소 : KAIST 정문술빌딩 220호

[1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [▶] .. [14]
             PREV NEXT WRITE

ⓒ Copyright 1999~   TECHNOTE-TOP / TECHNOTE.INC,

Copyright (c) Brain Science Research Center. All right reserved