Grounded Concept Development Using Introspective Atoms

In this paper we present a system that uses its underlying physiology, a hierarchical memory and a collection of memory management algorithms to learn concepts as cases and to build higher level concepts from experiences represented as sequences of atoms. Using a memory structure that requires all base memories to be grounded in introspective atoms, the system builds a set of grounded concepts that must all be formed from and applied to this same set of atoms. All interaction the system has with its environment must be represented by the system itself and therefore, given a complete ability to perceive its own physiological and mental processes, can be modeled and recreated.

• Type: Conference
• Year: 2003
• Where: MAICS
• Authors: Eric G. Berkowitz, Brian E. Mastenbrook
• Keywords: Artificial Intelligence, Hierarchical Memory, Introspective Atoms, MAICS 2003, Memory Management Algorithms