Time-series information and learning

Ryabko, Daniil

Type de document :

Communication dans un congrès avec actes

Titre :

Time-series information and learning

Auteur(s) :

Ryabko, Daniil [Auteur]
Sequential Learning [SEQUEL]

Titre de la manifestation scientifique :

ISIT - International Symposium on Information Theory

Ville :

Istanbul

Pays :

Turquie

Date de début de la manifestation scientifique :

2013

Date de publication :

2013

Discipline(s) HAL :

Informatique [cs]/Intelligence artificielle [cs.AI]

Résumé en anglais : [en]

Given a time series $X_1,\dots,X_n,\dots$ taking values in a large (high-dimensional) space $\cX$, we would like to find a function $f$ from $\cX$ to a small (low-dimensional or finite) space $\cY$ such that the time series ...
Lire la suite >Given a time series $X_1,\dots,X_n,\dots$ taking values in a large (high-dimensional) space $\cX$, we would like to find a function $f$ from $\cX$ to a small (low-dimensional or finite) space $\cY$ such that the time series $f(X_1),\dots,f(X_n),\dots$ retains all the information about the time-series dependence in the original sequence, or as much as possible thereof. This goal is formalized in this work, and it is shown that the target function $f$ can be found as the one that maximizes a certain quantity that can be expressed in terms of entropies of the series $(f(X_i))_{i\in\N}$. This quantity can be estimated empirically, and does not involve estimating the distribution on the original time series $(X_i)_{i\in\N}$.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Collections :

Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL

Time-series information and learning BibTeX CSV Excel RIS

Time-series information and learning

BibTeX

CSV

Excel

RIS