Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Adaptively learning probabilistic deterministic automata from data streams

Autor
de Balle, B.; Castro, J.; Gavaldà, R.
Tipus d'activitat
Article en revista
Revista
Machine learning
Data de publicació
2014-07
Volum
96
Número
1-2
Pàgina inicial
99
Pàgina final
127
DOI
https://doi.org/10.1007/s10994-013-5408-x Obrir en finestra nova
Repositori
http://hdl.handle.net/2117/28256 Obrir en finestra nova
URL
http://link.springer.com/article/10.1007%2Fs10994-013-5408-x Obrir en finestra nova
Resum
Markovian models with hidden state are widely-used formalisms for modeling sequential phenomena. Learnability of these models has been well studied when the sample is given in batch mode, and algorithms with PAC-like learning guarantees exist for specific classes of models such as Probabilistic Deterministic Finite Automata (PDFA). Here we focus on PDFA and give an algorithm for inferring models in this class in the restrictive data stream scenario: Unlike existing methods, our algorithm works i...
Citació
Balle, B.; Castro, J.; Gavaldà, R. Adaptively learning probabilistic deterministic automata from data streams. "Machine learning", Juliol 2014, vol. 96, núm. 1-2, p. 99-127.
Paraules clau
Data streams, PAC learning, PDFA, Probabilistic automata, Stream sketches
Grup de recerca
LARCA - Laboratori d'Algorísmia Relacional, Complexitat i Aprenentatge

Participants