This project implements an approach based on a research paper that addresses the problem of learning regular languages from examples. Regular languages have applications in natural language processing, robotics, and more. The research proposes a modified learning model and a new method using probabilistic finite state automata. The implemented Python code allows for learning shuffle ideals, a specific type of regular language. While efficient learning is challenging, the project provides tools for approximate learning under certain conditions. The code's practical applications include tasks in formal language theory and cryptography.
-
Notifications
You must be signed in to change notification settings - Fork 0
In this project we implement an algorithm provided in the paper "On the Learnability of Shuffle Ideals" which discusses the ability to PAC learn such shuffle ideals in a practical time complexity utilizing statistical queries.
mikethesilb/PAC-Learning-Shuffle-Ideals
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
In this project we implement an algorithm provided in the paper "On the Learnability of Shuffle Ideals" which discusses the ability to PAC learn such shuffle ideals in a practical time complexity utilizing statistical queries.
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published