Extracting finite structure from infinite language

Authors:
T. McQueen;A. A. Hopgood;T. J. Allen;J. A. Tepper
Affiliations:
School of Computing and Informatics, Nottingham Trent University, Burton Street, Nottingham NG1 4BU, UK;School of Computing and Informatics, Nottingham Trent University, Burton Street, Nottingham NG1 4BU, UK;School of Computing and Informatics, Nottingham Trent University, Burton Street, Nottingham NG1 4BU, UK;School of Computing and Informatics, Nottingham Trent University, Burton Street, Nottingham NG1 4BU, UK
Venue:
Knowledge-Based Systems
Year:
2005

Citing 7
Cited 2

Intelligent systems for engineers and scientists (2nd ed.)

Intelligent systems for engineers and scientists (2nd ed.)
Self-Organizing Maps

Self-Organizing Maps
Natural Language Grammatical Inference with Recurrent Neural Networks

IEEE Transactions on Knowledge and Data Engineering
Recursive self-organizing maps

Neural Networks - New developments in self-organizing maps
A study of grammatical inference

A study of grammatical inference
Finite state automata and simple recurrent networks

Neural Computation
Learning long-term dependencies with gradient descent is difficult

IEEE Transactions on Neural Networks

Knowledge representation with SOUL

Expert Systems with Applications: An International Journal
Segmentation of DNA using simple recurrent neural network

Knowledge-Based Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a novel connectionist memory-rule based model capable of learning the finite-state properties of an input language from a set of positive examples. The model is based upon an unsupervised recurrent self-organizing map with laterally interconnected neurons. A derivation of functional-equivalence theory is used that allows the model to exploit similarities between the future context of previously memorized sequences and the future context of the current input sequence. This bottom-up learning algorithm binds functionally related neurons together to form states. Results show that the model is able to learn the Reber grammar perfectly from a randomly generated training set and to generalize to sequences beyond the length of those found in the training set. ed sequences and the future context of the current input sequence. This bottom-up learning algorithm binds functionally related neurons together to form states. Results show that the model is able to learn the Reber grammar [A. Cleeremans, D. Schreiber, J. McClelland, Finite state automata and simple recurrent networks, Neural Computation, 1 (1989) 372-381] perfectly from a randomly generated training set and to generalize to sequences beyond the length of those found in the training set.