Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Learning deterministic finite automata with a smart state labeling evolutionary algorithm.

Simon M Lucas1, T Jeff Reynolds

  • 1Department of Computer Science, University of Essex, Wivenhoe Park, Colchester, Essex C04 35Q, UK. sml@essex.ac.uk

IEEE Transactions on Pattern Analysis and Machine Intelligence
|July 15, 2005
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same journal

Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentation.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

TraGraph-GS: Trajectory Graph-based Gaussian Splatting for Arbitrary Large-Scale Scene Rendering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

SWIFT: A Small-World Interaction Framework for Flow-Aware Trajectory Prediction in Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

This study introduces a new evolutionary algorithm for learning Deterministic Finite Automata (DFA). The novel method outperforms existing algorithms, especially when dealing with noisy training data in machine learning.

Area of Science:

  • Computer Science
  • Machine Learning
  • Artificial Intelligence

Background:

  • Learning Deterministic Finite Automata (DFA) from labeled strings is a challenging problem in machine learning.
  • This task is equivalent to learning regular languages by example, with applications in language modeling.

Purpose of the Study:

  • To introduce a novel evolutionary method for learning DFAs.
  • To compare the performance of this evolutionary method against the Evidence Driven State Merging (EDSM) algorithm.

Main Methods:

  • The proposed method evolves only the transition matrix of the DFA.
  • A deterministic procedure is used for optimal state label assignment.
  • Performance is evaluated on random DFA induction problems with varying sizes and densities.

Related Experiment Videos

  • The impact of noisy training data on both the evolutionary approach and EDSM is investigated.

    • Main Results:

    • On noise-free data, the evolutionary method shows superior performance compared to EDSM on small, sparse datasets.
    • In scenarios with noisy training data, the evolutionary method consistently outperforms EDSM and other leading algorithms.
    • The evolutionary approach demonstrates robustness against noisy data.

    Conclusions:

    • The novel evolutionary algorithm is an effective method for learning DFAs, particularly in the presence of noisy data.
    • This approach offers a competitive alternative to existing state-of-the-art DFA learning algorithms like EDSM.
    • The method shows promise for applications in language modeling and other areas requiring regular language identification.