Computational Mechanics: Pattern and Prediction, Structure and Simplicity

Abstract

Computational mechanics, an approach to structural complexity, defines a process's causal states and gives a procedure for finding them. We show that the causal-state representation--an $ε$-machine--is the minimal one consistent with accurate prediction. We establish several results on $ε$-machine optimality and uniqueness and on how $ε$-machines compare to alternative representations. Further results relate measures of randomness and structural complexity obtained from $ε$-machines to those from ergodic and information theories.