Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Spectral learning of general weighted automata via constrained matrix completion

Autor
B. Balle; Mohri, M.
Tipus d'activitat
Presentació treball a congrés
Nom de l'edició
26th Annual Conference on Neural Information Processing Systems
Any de l'edició
2013
Data de presentació
2012-12-04
Llibre d'actes
Advances in Neural Information Processing Systems 26: proceedings of the 2012 conference
Pàgina inicial
2168
Pàgina final
2176
Activitat premiada
Si
Projecte finançador
Pattern Analysis, Statistical Modelling, and Computational Learning 2 (PASCAL2)
Repositori
http://hdl.handle.net/2117/17754 Obrir en finestra nova
URL
http://books.nips.cc/papers/files/nips25/bibhtml/NIPS2012_1075.html Obrir en finestra nova
Resum
Many tasks in text and speech processing and computational biology require estimating functions mapping strings to real numbers. A broad class of such functions can be defined by weighted automata. Spectral methods based on the singular value decomposition of a Hankel matrix have been recently proposed for learning a probability distribution represented by a weighted automaton from a training sample drawn according to this same target distribution. In this paper, we show how spectral methods can...
Citació
B. Balle; Mohri, M. Spectral learning of general weighted automata via constrained matrix completion. A: Annual Conference on Neural Information Processing Systems. "Advances in Neural Information Processing Systems 26: proceedings of the 2012 conference". Lake Tahoe, Nevada: 2012, p. 2168-2176.
Grup de recerca
LARCA - Laboratori d'Algorísmia Relacional, Complexitat i Aprenentatge

Participants

  • De Balle Pigem, Borja  (autor ponent)
  • Mohri, Mehryar  (autor ponent)

Arxius