The notion of conceptual structure in CA rules that perform the density classification task (DCT) was introduced by . Here we investigate the role of process-symmetry in CAs that solve the DCT, in particular the idea of conceptual similarity, which defines a novel search space for CA rules. We report on two new process-symmetric one-dimensional rules for the DCT which have the highest "balanced" performance observed to date on this task, as well as the highest-performing CA known to perform the DCT in two dimensions. Finally, we investigate the more general problem of assessing how different learning strategies (based on evolution and coevolution, with and without spatial distribution), previously compared by , are suited to exploit conceptual structure in learning CAs to perform collective computation.
展开▼