Knowledge representation in neural networks

Recall the earlier definition of intelligence as doing the right thing at the right time, as judged by an outside human observer. As a key facilitator of intelligence, knowledge can then be defined as background information or general understanding (of a variety of domains) that enhances the ability to act intelligently, where domains include the natural, social, and even virtual worlds, as well as mathematics, music, art, etc. A knowledge representation is an encoding of this information or understanding in a particular substrate, such as a set of if-then rules, a semantic network, conditional probability tables, a Venn diagram, a mind map, or the axioms of formal logic. Thus, patterns (i.e., relationships among primitive elements) within the substrate correspond to patterns in the target domain. The relationships between the patterns (e.g., how each promotes or inhibits others) are key determinants of intelligence.