In this paper we introduce a formalism which combines reliability and complexity as performance measures for Intelligent Machines. For a given desired reliability, di erent algorithms may be available which are reliable enough. Hence it is important to have a means of choosing the algorithm of least cost among the reliable ones. By cost we do not mean CPU time only but other features such as memory space. Information-Based Complexity provides a solid formalism to deal with di erent sources of information, thus with distinct algorithms at all levels of the machine. A case study related to image processing illustrates the method.
Pedro U. Lima, George N. Saridis