Procedural Knowledge Representation (Black Box Hypothesis)

In contrast to declarative knowledge which can be read and modified by humans and all processes that know the format, procedural knowledge is in a machine-optimal representation that cannot be read or modified by humans or other internal processes.

Use of procedural knowledge in an agent raises the questions of whether the agent can "know what it knows" and the issue of penetrability of the knowledge. Use of this knowledge may not preclude the agent from this form of meta-knowledge and it certainly does not imply cognitive impenetrability. That the agent can exhibit behavior that it knows what it knows is illustrated in Soar by the instance that explained its actions. Cognitive impenetrability is not implied because for any operator learned, new, improved operators can be learned along with preference rules that lead to the emergence of cognitive penetrability. The precise bits corresponding to the original operator are neither understood nor changed, but the behavior exhibited by the operator has been penetrated.


These architectures employ an impenetrable representation:
Press UP to go the property list.

Press HOME to return to the Table of Contents.