Knowledge consolidation and inference in an integrated neuro-cognitive architecture

• Main Author: Oentaryo, Richard Jayadi
• Other Authors: Michel B. Pasquier
• Format: Theses and Dissertations
• Language: English
• Published: 2011
• Subjects: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence; DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition
• Online Access: https://hdl.handle.net/10356/43793
• Institution: Nanyang Technological University

Developing a general machine intelligence that can provide truly natural interaction and human-like cognition has been a major challenge in artificial intelligence research. To this end, cognitive architectures are increasingly investigated as generic blueprints for intelligent agents that can operate across different task domains. A variety of cognitive architectures have been formulated over the years, but there remains a need to further develop salient aspects of general intelligence, such as knowledge consolidation, system scalability, and metacognitive functions. This thesis first provides a comprehensive survey of the contemporary cognitive architectures, with systematic categorization of various design approaches and critical evaluations on their design properties, merits and shortcomings. Promising milestones and directions are also outlined, with emphasis on how consolidation, scalability and metacognition can help address the issues in the current cognitive architectures and contribute to the creation of better architectures/systems.