Learning Closed Signal Flow Graphs
Logic in Computer Science
2024-07-02 v1 Machine Learning
Abstract
We develop a learning algorithm for closed signal flow graphs - a graphical model of signal transducers. The algorithm relies on the correspondence between closed signal flow graphs and weighted finite automata on a singleton alphabet. We demonstrate that this procedure results in a genuine reduction of complexity: our algorithm fares better than existing learning algorithms for weighted automata restricted to the case of a singleton alphabet.
Keywords
Cite
@article{arxiv.2407.00245,
title = {Learning Closed Signal Flow Graphs},
author = {Ekaterina Piotrovskaya and Leo Lobski and Fabio Zanasi},
journal= {arXiv preprint arXiv:2407.00245},
year = {2024}
}
Comments
13 pages, 6 figures. An extended abstract for Learning and Automata workshop (LearnAut 2024)