Learning DFA from Simple Examples
 Rajesh Parekh,
 Vasant Honavar
 … show all 2 hide
Abstract
Efficient learning of DFA is a challenging research problem in grammatical inference. It is known that both exact and approximate (in the PAC sense) identifiability of DFA is hard. Pitt has posed the following open research problem: “Are DFA PACidentifiable if examples are drawn from the uniform distribution, or some other known simple distribution?” (Pitt, in Lecture Notes in Artificial Intelligence, 397, pp. 18–44, SpringerVerlag, 1989). We demonstrate that the class of DFA whose canonical representations have logarithmic Kolmogorov complexity is efficiently PAC learnable under the Solomonoff Levin universal distribution (m). We prove that the class of DFA is efficiently learnable under the PACS (PAC learning with simple examples) model (Denis, D'Halluin & Gilleron, STACS'96—Proceedings of the 13th Annual Symposium on the Theoretical Aspects of Computer Science, pp. 231–242, 1996) wherein positive and negative examples are sampled according to the universal distribution conditional on a description of the target concept. Further, we show that any concept that is learnable under Gold's model of learning from characteristic samples, Goldman and Mathias' polynomial teachability model, and the model of learning from example based queries is also learnable under the PACS model.
 Title
 Learning DFA from Simple Examples
 Journal

Machine Learning
Volume 44, Issue 12 , pp 935
 Cover Date
 200107
 DOI
 10.1023/A:1010822518073
 Print ISSN
 08856125
 Online ISSN
 15730565
 Publisher
 Kluwer Academic Publishers
 Additional Links
 Topics
 Keywords

 DFA inference
 exact identification
 characteristic sets
 PAC learning
 collusion
 Industry Sectors
 Authors

 Rajesh Parekh ^{(1)}
 Vasant Honavar ^{(2)}
 Author Affiliations

 1. Blue Martini Software, 2600 Campus Drive, San Mateo, CA, 94403, USA
 2. Department of Computer Science, Iowa State University, Ames, IA, 50011, USA