Learning and extracting initial mealy automata with a modular neural network model

Authors:
Peter Tiňo;Jozef Šajda
Affiliations:
-;-
Venue:
Neural Computation
Year:
1995

Citing 0
Cited 17

Analysis of dynamical recognizers

Neural Computation
Theory of neuromata

Journal of the ACM (JACM)
Predicting the Future of Discrete Sequences from Fractal Representations of the Past

Machine Learning
Rule Revision With Recurrent Neural Networks

IEEE Transactions on Knowledge and Data Engineering
Finite-state computation in analog neural networks: steps towards biologically plausible models?

Emergent neural computational architectures based on neuroscience
Robust Implementaion of Finite Automata by Recurrent RBF Networks

SOFSEM '00 Proceedings of the 27th Conference on Current Trends in Theory and Practice of Informatics
Finite-State Computation in Analog Neural Networks: Steps towards Biologically Plausible Models?

Emergent Neural Computational Architectures Based on Neuroscience - Towards Neuroscience-Inspired Computing
Recurrent neural networks with small weights implement definite memory machines

Neural Computation
Architectural bias in recurrent neural networks: fractal analysis

Neural Computation
A machine learning method for extracting symbolic knowledge from recurrent neural networks

Neural Computation
Incremental training of first order recurrent neural networks to predict a context-sensitive language

Neural Networks
Learning Beyond Finite Memory in Recurrent Networks of Spiking Neurons

Neural Computation
Rule Extraction from Recurrent Neural Networks: A Taxonomy and Review

Neural Computation
Attractive Periodic Sets in Discrete-Time Recurrent Networks (with Emphasis on Fixed-Point Stability and Bifurcations in Two-Neuron Networks)

Neural Computation
Stable Encoding of Finite-State Machines in Discrete-Time Recurrent Neural Nets with Sigmoid Units

Neural Computation
Analysis and Visualization of the Dynamics of Recurrent Neural Networks for Symbolic Sequences Processing

ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part II
Learning beyond finite memory in recurrent networks of spiking neurons

ICNC'05 Proceedings of the First international conference on Advances in Natural Computation - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

A hybrid recurrent neural network is shown to learn smallinitial mealy machines (that can be thought of as translationmachines translating input strings to corresponding output strings,as opposed to recognition automata that classify strings as eithergrammatical or nongrammatical) from positive training samples. Awell-trained neural net is then presented once again with thetraining set and a Kohonen self-organizing map with the "star"topology of neurons is used to quantize recurrent network statespace into distinct regions representing corresponding states of amealy machine being learned. This enables us to extract the learnedmealy machine from the trained recurrent network. One neuralnetwork (Kohonen self-organizing map) is used to extract meaningfulinformation from another network (recurrent neural network).