Past-future information bottleneck in dynamical systems. Creutzig, F., Globerson, A., & Tishby, N.
doi  abstract   bibtex   
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 se-lectively 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 correspond-ing 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.
@article{Creutzig,
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 se-lectively 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 correspond-ing 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.},
author = {Creutzig, Felix and Globerson, Amir and Tishby, Naftali},
doi = {10.1103/PhysRevE.79.041925},
file = {:Users/brekels/Documents/Mendeley Desktop/Past-future information bottleneck in dynamical systems - Creutzig, Globerson, Tishby.pdf:pdf},
title = {{Past-future information bottleneck in dynamical systems}}
}

Downloads: 0