Ignacio Lopez, Ricardo Sanz, Carlos Hernandez
The question of measuring intelligence in artifacts and, in particular, evaluating architectures for it, requires not just an understanding of the very nature of intelligence quite elu- sive objective, indeed but an appropriate stance for evalua- tion. In this paper we argue that it is not just the case that architectures provide intelligence, but that they really pro- vide a substrate for intelligent behavior in the execution of a particular task. The measuring-intelligence-for-autonomy position becomes maximally relevant in the context of the in- creased uncertainty levels that the upcoming challenging ap- plications are posing to cognitive architectures. This fits our understanding of intelligence as the capability of maximizing information utility.
Subjects: 2. Architectures; 9. Foundational Issues
Submitted: May 15, 2007