Title :
Towards A Novel Integrated Neuro-Cognitive Architecture (INCA)
Author :
Oentaryo, Richard J. ; Pasquier, Michel
Author_Institution :
Centre for Comput. Intell., Nanyang Technol. Univ., Singapore
Abstract :
Artificial intelligence research is now flourishing which aims at achieving general, human-level intelligence. Accordingly, cognitive architectures are increasingly employed as blueprints for building intelligent agents to be endowed with various perceptive and cognitive abilities. This paper presents a novel integrated neuro-cognitive architecture (INCA) which emulate the putative functional aspects of various salient brain sub-systems via a learning memory modeling approach. The strength of INCA lies in self-organizing connectionist learning to induce high-level symbolic knowledge autonomously, and support for meta-cognitive functions. Its overall operations are governed by its consolidation and inference cycles, which posit a human-plausible way for forming and exploiting knowledge.
Keywords :
artificial intelligence; cognitive systems; inference mechanisms; learning systems; neural net architecture; artificial intelligence research; inference cycles; integrated neuro-cognitive architecture; learning memory modeling approach; meta-cognitive functions; salient brain subsystems; self-organizing connectionist learning; Neural networks;
Conference_Titel :
Neural Networks, 2008. IJCNN 2008. (IEEE World Congress on Computational Intelligence). IEEE International Joint Conference on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4244-1820-6
Electronic_ISBN :
1098-7576
DOI :
10.1109/IJCNN.2008.4634058