Extraction of Rules from Discrete-time Recurrent Neural Networks

Extraction of Rules from Discrete-time Recurrent Neural Networks (1996)

by Christian W. Omlin , C. Lee Giles

Citations:

57 - 15 self

User correction supplied by mph

Datum	Value	Source
TITLE	Extraction of Rules from Discrete-time Recurrent Neural Networks	user correction
AUTHOR NAME	Christian W. Omlin	user correction
AUTHOR AFFIL	NEC Research Institute	user correction
AUTHOR NAME	C. Lee Giles	user correction
AUTHOR AFFIL	NEC Research Institute	user correction
ABSTRACT	The extraction of symbolic knowledge from trained neural networks and the direct encoding of (partial) knowledge into networks prior to training are important issues. They allow the exchange of information between symbolic and connectionist knowledge representations. The focas of this paper is on the quality of the rules that are extracted from recurrent neural networks. Discrete-time recurrent neural networks can be trained to correctly classify strings of a regular language. Rules defining the learned grammar can be extracted from networks in the form of deterministic finite-state automata (DFAs) by applying clustering algorithms in the output space of recurrent state neurons. Our algorithm can extract different finite-state automata that are consistent with a training set from the same network. We compare the generalization performances of these different models and the trained network and we introduce a heuristic that permits us to choose among the consistent DFAs the model which best approximates the learned regular grammar.	user correction
YEAR	1996	user correction
CITATIONS	33 found	ParsCit 1.0