On-line identification and reconstruction of finite automata with generalized recurrent neural networks

Authors:
Ivan Gabrijel;Andrej Dobnikar
Affiliations:
Faculty of Computer and Information Science, University of Ljubljana, Trzaska c. 25, SI-1001 Ljubljana, Slovenia;Faculty of Computer and Information Science, University of Ljubljana, Trzaska c. 25, SI-1001 Ljubljana, Slovenia
Venue:
Neural Networks
Year:
2003

Citing 28
Cited 5

Adaptive filter theory

Adaptive filter theory
System identification: theory for the user

System identification: theory for the user
Adaptive control using neural networks

Neural networks for control
Original Contribution: Optimal filtering algorithms for fast learning in feedforward neural networks

Neural Networks
A recurrent neural network controller and learning algorithm for the on-line learning control of autonomous underwater vehicles

Neural Networks
Learning dynamics: system identification for perceptually challenged agents

Artificial Intelligence - Special volume on computational research on interaction and agency, part 1
Gradient-based learning algorithms for recurrent networks and their computational complexity

Backpropagation
Extraction of rules from discrete-time recurrent neural networks

Neural Networks
Bounds on the complexity of recurrent neural network implementations of finite state machines

Neural Networks
Representation of finite state automata in recurrent radial basis function networks

Machine Learning
On the computational power of recurrent neural networks for structures

Neural Networks
Analysis of dynamical recognizers

Neural Computation
Exactly Learning Automata of Small Cover Time

Machine Learning - Special issue on the eighth annual conference on computational learning theory, (COLT '95)
Long short-term memory

Neural Computation
Efficient learning of typical finite automata from random walks

Information and Computation
Theory of neuromata

Journal of the ACM (JACM)
Dynamic on-line clustering and state extraction: an approach to symbolic learning

Neural Networks
Correction to proof that recurrent neural networks can robustly recognize only regular languages

Neural Computation
Automata and neural networks

The handbook of brain theory and neural networks
Recurrent networks: supervised learning

The handbook of brain theory and neural networks
On redundancy in neural architecture: dynamics of a simple module-based neural network and initial-state independence

Neural Networks - Special issue on organisation of computation in brain-like systems
Stable behavior in a recurrent neural network for a finite state machine

Neural Networks
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Introduction to Automata Theory, Languages and Computability

Introduction to Automata Theory, Languages and Computability
Theory and Design Switching Circ

Theory and Design Switching Circ
The dynamics of discrete-time computation, with application to recurrent neural networks and finite state machine extraction

Neural Computation
On-line training of recurrent neural networks with continuous topology adaptation

IEEE Transactions on Neural Networks
Recurrent neural-network training by a learning automaton approach for trajectory learning and control system design

IEEE Transactions on Neural Networks

Impact of Learning on the Structural Properties of Neural Networks

ICANNGA '07 Proceedings of the 8th international conference on Adaptive and Natural Computing Algorithms, Part II
Structural Properties of Recurrent Neural Networks

Neural Processing Letters
Identification of finite state automata with a class of recurrent neural networks

IEEE Transactions on Neural Networks
Generation of a clustering ensemble based on a gravitational self-organising map

Neurocomputing
Selective Recurrent Neural Network

Neural Processing Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper finite automata are treated as general discrete dynamical systems from the viewpoint of systems theory. The unconditional on-line identification of an unknown finite automaton is the problem considered. A generalized architecture of recurrent neural networks with a corresponding on-line learning scheme is proposed as a solution to the problem. An on-line rule-extraction algorithm is further introduced. The architecture presented, the on-line learning scheme and the on-line rule-extraction method are tested on different, strongly connected automata, ranging from a very simple example with two states only to a more interesting and complex one with 64 states; the results of both training and extraction processes are very promising.