Publication View

Embedded-Particle Computation in Evolved Cellular Automata (1998)

Abstract
this paper we focus on how these CAs implement the emergent computational strategies for performing a task. In particular, we develop a class of embedded-particle models to describe the computational strategies implemented by particular CAs. To do this, we use the computational mechanics framework of Crutchfield and Hanson [2, 6], in which a CA's information processing is described in terms of regular domains, embedded particles, and their interactions. We then evaluate this class of models by comparing their computational performance to that of the CAs they model. The results demonstrate, via a generally close quantitative agreement between the CAs and the embedded particle models, that this new model class captures the significant functional features in the CAs' space-time behavior that underlie the CAs' computational capability and evolutionary fitness. 2 CAs and Computation

Publication details
Download http://citeseer.ist.psu.edu/141149.html
Source http://unlser1.unl.csi.cuny.edu/~archives/postscripts/ai/ca/epcieca.ps
Publisher unknown
Contributors The Pennsylvania State University CiteSeer Archives
Repository CiteSeer (United States)
Keywords Wim Hordijk,James P. Crutchfield,Melanie Mitchell Embedded-Particle Computation in Evolved Cellular Automata
Language Englisch