Analysis about Intelligence Evaluation Based on Computational Semiotics Theory

摘要

The paper discussed methods for evaluating the intelligence of intelligent systems by means of computational semiotics concepts. Instead of looking at the system as a black box and testing its behavior, the process described in this paper focus on architectural details of structures, organizations, processes and algorithms used in the construction of the intelligent system, evaluating the impact of using these elements in the overall intelligent behavior exhibited by the system. It proposes then an "insider" type of metrics that, coupled to "outsider" metrics, we hope will be important for the determination of general metrics of intelligence in intelligent systems.