Please use this identifier to cite or link to this item:
http://hdl.handle.net/10261/30551
Share/Export:
SHARE CORE BASE | |
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE | |
Title: | An algebraic framework to represent finite state machines in single-layer recurrent neural networks |
Authors: | Alquézar Mancho, Renato CSIC ; Sanfeliu, Alberto CSIC ORCID | Keywords: | Pattern recognition | Issue Date: | 1995 | Publisher: | Massachusetts Institute of Technology | Citation: | Neural Computation 7(5): 931-949 (1995) | Abstract: | 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). | Publisher version (URL): | http://dx.doi.org/10.1162/neco.1995.7.5.931 | URI: | http://hdl.handle.net/10261/30551 | DOI: | 10.1162/neco.1995.7.5.931 | ISSN: | 0899-7667 |
Appears in Collections: | (IRII) Artículos |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
algebraic framework.pdf | 303,1 kB | Adobe PDF | View/Open |
CORE Recommender
WEB OF SCIENCETM
Citations
19
checked on Feb 22, 2024
Page view(s)
343
checked on Apr 24, 2024
Download(s)
318
checked on Apr 24, 2024
Google ScholarTM
Check
Altmetric
Altmetric
WARNING: Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.