DocumentCode :
186197
Title :
Tutorial on compositionality and self-organization in cognitive minds: Dynamic neural network models and robotics experiments (ICDL-EPIROB 2014, Genova, Oct. 13th, 2014) Jun Tani, KAIST, South Korea
Author :
Jun Tani
Author_Institution :
KAIST, Daejeon, South Korea
fYear :
2014
fDate :
13-16 Oct. 2014
Firstpage :
1
Lastpage :
3
Abstract :
The most pressing question about cognitive brains is how they support the compositionality that enables combinatorial manipulations of images, thoughts and actions. When addressing this problem with synthetic modeling, the conventional idea prevalent in artificial intelligence and cognitive science, generally, is to assume hybrid systems and corresponding neural network models, where higher-order cognition is realized by means of symbolic representation and lower sensory-motor processes by analogue processing. However, the crucial problem with such approaches is that the symbols represented at higher order cognitive levels cannot be grounded naturally in sensory-motor reality. The former are defined in a discrete space without any metric and the latter are defined in a continuous space with a physical metric. These, therefore, cannot directly interact with each other, regardless of the interface that is assigned between them. In facing with this problem, a recent promising proposal in the community of embodied cognition and developmental robotics is to reconstruct higher-order cognition by means of continuous neuro-dynamic systems that can elaborate delicate interactions with the sensory-motor level while sharing the same metric space. In fact a set of neuro-robotics experiments - including hierarchical learning of compositional action skills, associative learning between proto-language - have shown that the compositionality necessary for higher-order cognitive tasks can be acquired by means of self-organizing dynamic structures, via interactive learning between the top-down intentional process of acting on the physical world and the bottom-up recognition of perceptual reality.
Keywords :
learning (artificial intelligence); neurocontrollers; robots; analogue processing; artificial intelligence; associative learning; cognitive brain; cognitive mind; cognitive science; developmental robotics; dynamic neural network models; embodied cognition; hierarchical learning; higher-order cognition; perceptual reality; robotics experiments; sensory-motor reality; symbolic representation; synthetic modeling; Biological neural networks; Brain models; Cognition; Measurement; Robot sensing systems;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Development and Learning and Epigenetic Robotics (ICDL-Epirob), 2014 Joint IEEE International Conferences on
Conference_Location :
Genoa
Type :
conf
DOI :
10.1109/DEVLRN.2014.6982942
Filename :
6982942
Link To Document :
بازگشت