This paper considers the problem of identification of an interval model for an unknown static function using a finite batch of stochastic input–output data {u(i),y(i)}, i=1,…,N. The criterion used for identification is that the width of the interval output of the model should be minimized, while containing a given fraction of the observed outputs y(i). We show that, for suitable finite N, the resulting model will be reliable, that is it will explain any other unseen output, up to a given and arbitrary high probability.
Learning noisy functions via interval models / Calafiore, Giuseppe Carlo. - In: SYSTEMS & CONTROL LETTERS. - ISSN 0167-6911. - STAMPA. - 59:7(2010), pp. 404-413. [10.1016/j.sysconle.2010.05.003]
Learning noisy functions via interval models
CALAFIORE, Giuseppe Carlo
2010
Abstract
This paper considers the problem of identification of an interval model for an unknown static function using a finite batch of stochastic input–output data {u(i),y(i)}, i=1,…,N. The criterion used for identification is that the width of the interval output of the model should be minimized, while containing a given fraction of the observed outputs y(i). We show that, for suitable finite N, the resulting model will be reliable, that is it will explain any other unseen output, up to a given and arbitrary high probability.Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2376137
Attenzione
Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo