University of Hertfordshire

By the same authors

Causal Blankets: Theory and Algorithmic Framework

Research output: Contribution to conferencePoster

Documents

View graph of relations
Original languageEnglish
Publication statusPublished - 18 Sep 2020
EventInternational Workshop on Active Inference - Online , Ghent, Belgium
Duration: 14 Sep 202018 Sep 2020

Conference

ConferenceInternational Workshop on Active Inference
Abbreviated titleIWAI
CountryBelgium
CityGhent
Period14/09/2018/09/20

Abstract

We introduce a novel framework to identify perception-action loops (PALOs) directly from data based on the principles of computational mechanics. Our approach is based on the notion of causal blanket, which captures sensory and active variables as dynamical sufficient statistics -- i.e. as the "differences that make a difference." Moreover, our theory provides a broadly applicable procedure to construct PALOs that requires neither a steady-state nor Markovian dynamics. Using our theory, we show that every bipartite stochastic process has a causal blanket, but the extent to which this leads to an effective PALO formulation varies depending on the integrated information of the bipartition.

ID: 22562520