Please use this identifier to cite or link to this item: http://hdl.handle.net/10261/30551
Share/Impact:
Título : An algebraic framework to represent finite state machines in single-layer recurrent neural networks
Autor : Alquézar, René, Sanfeliu Cortés, Alberto
Palabras clave : Pattern recognition
Fecha de publicación : 1995
Editor: Massachusetts Institute of Technology
Resumen: In this paper we present an algebraic framework to represent finite state machines (FSMs) in single-layer recurrent neural networks (SLRNNs), which unifies and generalizes some of the previous proposals. This framework is based on the formulation of both the state transition function and the output function of an FSM as a linear system of equations, and it permits an analytical explanation of the representational capabilities of first-order and higher-order SLRNNs. The framework can be used to insert symbolic knowledge in RNNs prior to learning from examples and to keep this knowledge while training the network. This approach is valid for a wide range of activation functions, whenever some stability conditions are met. The framework has already been used in practice in a hybrid method for grammatical inference reported elsewhere (Sanfeliu and Alquézar 1994).
Versión del editor: http://dx.doi.org/10.1162/neco.1995.7.5.931
URI : http://hdl.handle.net/10261/30551
ISSN: 0899-7667
DOI: 10.1162/neco.1995.7.5.931
Citación : Neural Computation 7(5): 931-949 (1995)
Appears in Collections:(IRII) Artículos

Files in This Item:
File Description SizeFormat 
algebraic framework.pdf303,1 kBAdobe PDFView/Open
Show full item record
 
CSIC SFX LinksSFX Query


Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.