Past-future information bottleneck in dynamical systems.
Phys Rev E Stat Nonlin Soft Matter Phys
; 79(4 Pt 1): 041925, 2009 Apr.
Article
en En
| MEDLINE
| ID: mdl-19518274
ABSTRACT
Biological systems need to process information in real time and must trade off accuracy of presentation and coding costs. Here we operationalize this trade-off and develop an information-theoretic framework that selectively extracts information of the input past that is predictive about the output future, obtaining a generalized eigenvalue problem. Thereby, we unravel the input history in terms of structural phase transitions corresponding to additional dimensions of a state space. We elucidate the relation to canonical correlation analysis and give a numerical example. Altogether, this work relates information-theoretic optimization to the joint problem of system identification and model reduction.
Search on Google
Banco de datos:
MEDLINE
Asunto principal:
Predicción
/
Modelos Biológicos
/
Modelos Teóricos
Tipo de estudio:
Prognostic_studies
Idioma:
En
Año:
2009
Tipo del documento:
Article