The evolution of parallel cellular machines: Toward evolware

The historical idea of evolving machines has recently resurfaced as the nascent field of bio-inspired systems and evolvable hardware. This paper describes the cellular programming approach used to evolve parallel cellular machines, presenting its application to six computational problems: density, synchronization, ordering, boundary computation, thinning and random number generation. Our results show that successful machines can be evolved to solve these tasks. The methodology described herein represents one possible approach to attaining truly evolving ware, evolware, with current implementations centering on hardware, while raising the possibility of using other forms in the future, such as bioware. The paper presents work in progress, the aim being to give an account of results obtained to date, ending with a list of several open issues for future research.