Dynamic information in uncertain and changing worlds

Abstract

A general theory for information processing by organisms living in uncertain and changing worlds is developed. The three fundamental properties of the theory are: (i) the use of a memory parameter that allows the organism to forget the more distant past, (ii) a succinct representation of encounters and information and (iii) flexibility in the estimates of parameters by including the uncertainty in these estimates in a consistent manner. The theory is developed using Bayesian methods (but can also be applied to maximum likelihood estimation) and is applied to the encounter models standardly used in ecology (Poisson, binomial, and negative binomial). Two applications are discussed: (i) patch selection and the matching rule and (ii) superparasitism by a parasitoid.