Communications of the ACM
Algorithmic information theory
Algorithmic information theory
Learning regular sets from queries and counterexamples
Information and Computation
Elements of information theory
Elements of information theory
Random DFA's can be approximately learned from sparse uniform examples
COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
The calculi of emergence: computation, dynamics and induction
Proceedings of the NATO advanced research workshop and EGS topical workshop on Chaotic advection, tracer dynamics and turbulent dispersion
Learning finite machines with self-clustering recurrent networks
Neural Computation
Improving Generalization with Active Learning
Machine Learning - Special issue on structured connectionist systems
Model Uncertainty in Discrete Event Systems
SIAM Journal on Control and Optimization
Testing by means of inductive program learning
ACM Transactions on Software Engineering and Methodology (TOSEM)
Stochastic sequential machine synthesis targeting constrained sequence generation
DAC '96 Proceedings of the 33rd annual Design Automation Conference
Analysis of dynamical recognizers
Neural Computation
System identification (2nd ed.): theory for the user
System identification (2nd ed.): theory for the user
On the notion of interestingness in automated mathematical discovery
International Journal of Human-Computer Studies - Special issue on Machine Discovery
Field Guide to Dynamical Recurrent Networks
Field Guide to Dynamical Recurrent Networks
Introduction To Automata Theory, Languages, And Computation
Introduction To Automata Theory, Languages, And Computation
Theoretical Computer Science - Special issue: Algorithmic learning theory
Introduction to probabilistic automata (Computer science and applied mathematics)
Introduction to probabilistic automata (Computer science and applied mathematics)
Rule Extraction from Recurrent Neural Networks: A Taxonomy and Review
Neural Computation
Spatiotemporal Connectionist Networks: A Taxonomy and Review
Neural Computation
A dynamic interaction between machine learning and the philosophy of science
Minds and Machines - Machine learning as experimental philosophy of science
Cluster Analysis
A bibliographical study of grammatical inference
Pattern Recognition
IEEE Transactions on Neural Networks
IEEE Transactions on Neural Networks
LSTM recurrent networks learn simple context-free and context-sensitive languages
IEEE Transactions on Neural Networks
Improving procedures for evaluation of connectionist context-free language predictors
IEEE Transactions on Neural Networks
Markovian architectural bias of recurrent neural networks
IEEE Transactions on Neural Networks
Elman Backpropagation as Reinforcement for Simple Recurrent Networks
Neural Computation
A robust extended Elman backpropagation algorithm
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
| Hi-index | 0.00 |
This letter presents an algorithm, CrySSMEx, for extracting minimal finite state machine descriptions of dynamic systems such as recurrent neural networks. Unlike previous algorithms, CrySSMEx is parameter free and deterministic, and it efficiently generates a series of increasingly refined models. A novel finite stochastic model of dynamic systems and a novel vector quantization function have been developed to take into account the state-space dynamics of the system. The experiments show that (1) extraction from systems that can be described as regular grammars is trivial, (2) extraction from high-dimensional systems is feasible, and (3) extraction of approximative models from chaotic systems is possible. The results are promising, and an analysis of shortcomings suggests some possible further improvements. Some largely overlooked connections, of the field of rule extraction from recurrent neural networks, to other fields are also identified.