Loading...
Loading...

Go to the content (press return)

Bootstrapping and learning PDFA in data streams

Author
B. Balle; Castro, J.; Gavaldà, R.
Type of activity
Presentation of work at congresses
Name of edition
11th International Conference on Grammatical Inference
Date of publication
2012
Presentation's date
2012-09-07
Book of congress proceedings
Proceedings of the Eleventh International Conference on Grammatical Inference
First page
34
Last page
48
Rewarded activity
Yes
Repository
http://hdl.handle.net/2117/17434 Open in new window
URL
http://jmlr.csail.mit.edu/proceedings/papers/v21/balle12a/balle12a.pdf Open in new window
Abstract
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 specic classes of models such as Probabilistic Deterministic Finite Automata (PDFA). Here we focus on PDFA and give an algorithm for infering models in this class under the stringent data stream scenario: unlike existing methods, our algorithm works inc...
Citation
B. Balle; Castro, J.; Gavaldà, R. Bootstrapping and learning PDFA in data streams. A: International Colloquim on Grammatical Inference. "Proceedings of the Eleventh International Conference on Grammatical Inference". Washington: 2012, p. 34-48.
Group of research
LARCA - Laboratory of Relational Algorithmics, Complexity and Learnability

Participants

Attachments