Chapter

Artificial Neural Networks: Formal Models and Their Applications – ICANN 2005

Volume 3697 of the series Lecture Notes in Computer Science pp 503-508

CrySSMEx, a Novel Rule Extractor for Recurrent Neural Networks: Overview and Case Study

  • Henrik JacobssonAffiliated withCarnegie Mellon UniversitySchool of Humanities and Informatics, University of Skövde
  • , Tom ZiemkeAffiliated withCarnegie Mellon UniversitySchool of Humanities and Informatics, University of Skövde

* Final gross prices may vary according to local VAT.

Get Access

Abstract

In this paper, it will be shown that it is feasible to extract finite state machines in a domain of, for rule extraction, previously unencountered complexity. The algorithm used is called the Crystallizing Substochastic Sequential Machine Extractor, or CrySSMEx. It extracts the machine from sequence data generated from the RNN in interaction with its domain. CrySSMEx is parameter free, deterministic and generates a sequence of increasingly deterministic extracted stochastic models until a fully deterministic machine is found.