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

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.

• Type: Conference
• Year: 2005
• Where: ICANN
• Authors: Henrik Jacobsson, Tom Ziemke
• Keywords: Deterministic, Deterministic Machine, ICANN 2005, Sequential Machine Extractor