In this paper we present a novel algorithm, CarpeDiem. It significantly improves on the time complexity of Viterbi algorithm, preserving the optimality of the result. This fact has consequences on Machine Learning systems that use Viterbi algorithm during learning or classification. We show how the algorithm applies to the Supervised Sequential Learning task and, in particular, to the HMPerceptron algorithm. We illustrate CarpeDiem in full details, and provide experimental results that support the proposed approach.

CarpeDiem: an Algorithm for the Fast Evaluation of SSL Classifiers

ESPOSITO, Roberto;RADICIONI, DANIELE PAOLO
2007-01-01

Abstract

In this paper we present a novel algorithm, CarpeDiem. It significantly improves on the time complexity of Viterbi algorithm, preserving the optimality of the result. This fact has consequences on Machine Learning systems that use Viterbi algorithm during learning or classification. We show how the algorithm applies to the Supervised Sequential Learning task and, in particular, to the HMPerceptron algorithm. We illustrate CarpeDiem in full details, and provide experimental results that support the proposed approach.
CarpeDiem: an Algorithm for the Fast Evaluation of SSL Classifiers
Corvallis - Oregon - USA
24-6-2007
Proceedings of the 24th Annual International Conference on Machine Learning
ACM
227
257
264
9781595937933
http://portal.acm.org/citation.cfm?id=1273529
Viterbi algorithm; Supervised Sequential Learning; Dynamic programming
R. ESPOSITO; D. RADICIONI
File in questo prodotto:
File Dimensione Formato  
esposito07carpediem.pdf

Accesso riservato

Tipo di file: POSTPRINT (VERSIONE FINALE DELL’AUTORE)
Dimensione 728.04 kB
Formato Adobe PDF
728.04 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2318/32079
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 7
  • ???jsp.display-item.citation.isi??? ND
social impact