Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
- Fernando E. Rosas
- Pedro A.M. Mediano
- Martin Biehl
- Shamil Chandaria
- Daniel Polani
View graph of relations
Original language | English |
---|
Title of host publication | Active Inference - First International Workshop, IWAI 2020, Co-located with ECML/PKDD 2020, Proceedings |
---|
Editors | Tim Verbelen, Pablo Lanillos, Christopher L. Buckley, Cedric De Boom |
---|
Publisher | Springer Science and Business Media Deutschland GmbH |
---|
Pages | 187-198 |
---|
Number of pages | 12 |
---|
ISBN (Print) | 9783030649180 |
---|
DOIs | |
---|
Publication status | Published - 18 Dec 2020 |
---|
Event | 1st International Workshop on Active Inference, IWAI 2020 held in conjunction with the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML-PKDD 2020 - Ghent, Belgium Duration: 14 Sep 2020 → 14 Sep 2020 |
---|
Name | Communications in Computer and Information Science |
---|
Volume | 1326 |
---|
ISSN (Print) | 1865-0929 |
---|
ISSN (Electronic) | 1865-0937 |
---|
Conference | 1st International Workshop on Active Inference, IWAI 2020 held in conjunction with the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML-PKDD 2020 |
---|
Country | Belgium |
---|
City | Ghent |
---|
Period | 14/09/20 → 14/09/20 |
---|
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.” Furthermore, 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.
Notes
Funding Information:
F.R. was supported by the Ad Astra Chandaria foundation. P.M. was funded by the Wellcome Trust (grant no. 210920/Z/18/Z). M.B. was supported by a grant from Tem-pleton World Charity Foundation, Inc. (TWCF). The opinions expressed in this publication are those of the authors and do not necessarily reflect the views of TWCF.
Publisher Copyright:
© 2020, Springer Nature Switzerland AG.
This is a post-peer-review, pre-copyedit version of Rosas, F. E., Mediano, P. A. M., Biehl, M., Chandaria, S., & Polani, D. (2020). Causal blankets: Theory and algorithmic framework. In T. Verbelen, P. Lanillos, C. L. Buckley, & C. De Boom (Eds.), Active Inference - First International Workshop, IWAI 2020, Co-located with ECML/PKDD 2020, Proceedings (pp. 187-198). (Communications in Computer and Information Science; Vol. 1326). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-64919-7_19
ID: 24486202