On the Use of Randomization for System of Systems (SoS) Design of Intelligent Machines

This paper takes a system of systems (SoS) approach to the realization of machine intelligence. Random differences are learned by the system, generalized, and made available for subsequent replay in design transformations. It is empirically demonstrated that cross-domain symmetries can play a major role in design generation in particular and in the design of SoSs in general. The fundamental theory of randomization is the science, which underpins the practice. The approach is illustrated by an example of the design of a refrigeration system.