Advancing Deep Knowledge Integration
The field of artificial intelligence is traditionally divided into two broad paradigms. On one hand there are symbolic, formal, procedural, deterministic, and/or rule-based methods that often rely on a set of atomic elements and rules operating on those elements. Sometimes they are as complex as a comprehensive reasoning system. It is relatively effortless to provide a few manual instructions to these systems, however, these instructions (i.e., rules) are labor-intensive and become unfeasibly time-consuming as the complexity of the system grows beyond a certain point. In addition, symbolic systems do not learn from experience or data. On the other hand, adaptive systems do learn from data a system is exposed to but are not immediately equipped to receive simple instructions from the wealth of stored information, for instance, databases. The process of enabling adaptive systems to incorporate stored facts is called knowledge integration that this project endeavors to improve.