Symbolic processing in neural networks
Autor(a) principal: | |
---|---|
Data de Publicação: | 2003 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Journal of the Brazilian Computer Society |
Texto Completo: | http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0104-65002003000100005 |
Resumo: | In this paper we show that programming languages can be translated into recurrent (analog, rational weighted) neural nets. Implementation of programming languages in neural nets turns to be not only theoretical exciting, but has also some practical implications in the recent efforts to merge symbolic and sub symbolic computation. To be of some use, it should be carried in a context of bounded resources. Herein, we show how to use resource bounds to speed up computations over neural nets, through suitable data type coding like in the usual programming languages. We introduce data types and show how to code and keep them inside the information flow of neural nets. Data types and control structures are part of a suitable programming language called NETDEF. Each NETDEF program has a specific neural net that computes it. These nets have a strong modular structure and a synchronization mechanism allowing sequential or parallel execution of subnets, despite the massive parallel feature of neural nets. Each instruction denotes an independent neural net. There are constructors for assignment, conditional and loop instructions. Besides the language core, many other features are possible using the same method. |
id |
UFRGS-28_57ee26b613d8375eb706a288a0b17eed |
---|---|
oai_identifier_str |
oai:scielo:S0104-65002003000100005 |
network_acronym_str |
UFRGS-28 |
network_name_str |
Journal of the Brazilian Computer Society |
repository_id_str |
|
spelling |
Symbolic processing in neural networksNeural NetworksNeural ComputationSymbolic ProcessingNETDEFIn this paper we show that programming languages can be translated into recurrent (analog, rational weighted) neural nets. Implementation of programming languages in neural nets turns to be not only theoretical exciting, but has also some practical implications in the recent efforts to merge symbolic and sub symbolic computation. To be of some use, it should be carried in a context of bounded resources. Herein, we show how to use resource bounds to speed up computations over neural nets, through suitable data type coding like in the usual programming languages. We introduce data types and show how to code and keep them inside the information flow of neural nets. Data types and control structures are part of a suitable programming language called NETDEF. Each NETDEF program has a specific neural net that computes it. These nets have a strong modular structure and a synchronization mechanism allowing sequential or parallel execution of subnets, despite the massive parallel feature of neural nets. Each instruction denotes an independent neural net. There are constructors for assignment, conditional and loop instructions. Besides the language core, many other features are possible using the same method.Sociedade Brasileira de Computação2003-04-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersiontext/htmlhttp://old.scielo.br/scielo.php?script=sci_arttext&pid=S0104-65002003000100005Journal of the Brazilian Computer Society v.8 n.3 2003reponame:Journal of the Brazilian Computer Societyinstname:Sociedade Brasileira de Computação (SBC)instacron:UFRGS10.1590/S0104-65002003000100005info:eu-repo/semantics/openAccessNeto,João PedroSiegelmann,Hava T.Costa,J.Félixeng2004-09-16T00:00:00Zoai:scielo:S0104-65002003000100005Revistahttps://journal-bcs.springeropen.com/PUBhttps://old.scielo.br/oai/scielo-oai.phpjbcs@icmc.sc.usp.br1678-48040104-6500opendoar:2004-09-16T00:00Journal of the Brazilian Computer Society - Sociedade Brasileira de Computação (SBC)false |
dc.title.none.fl_str_mv |
Symbolic processing in neural networks |
title |
Symbolic processing in neural networks |
spellingShingle |
Symbolic processing in neural networks Neto,João Pedro Neural Networks Neural Computation Symbolic Processing NETDEF |
title_short |
Symbolic processing in neural networks |
title_full |
Symbolic processing in neural networks |
title_fullStr |
Symbolic processing in neural networks |
title_full_unstemmed |
Symbolic processing in neural networks |
title_sort |
Symbolic processing in neural networks |
author |
Neto,João Pedro |
author_facet |
Neto,João Pedro Siegelmann,Hava T. Costa,J.Félix |
author_role |
author |
author2 |
Siegelmann,Hava T. Costa,J.Félix |
author2_role |
author author |
dc.contributor.author.fl_str_mv |
Neto,João Pedro Siegelmann,Hava T. Costa,J.Félix |
dc.subject.por.fl_str_mv |
Neural Networks Neural Computation Symbolic Processing NETDEF |
topic |
Neural Networks Neural Computation Symbolic Processing NETDEF |
description |
In this paper we show that programming languages can be translated into recurrent (analog, rational weighted) neural nets. Implementation of programming languages in neural nets turns to be not only theoretical exciting, but has also some practical implications in the recent efforts to merge symbolic and sub symbolic computation. To be of some use, it should be carried in a context of bounded resources. Herein, we show how to use resource bounds to speed up computations over neural nets, through suitable data type coding like in the usual programming languages. We introduce data types and show how to code and keep them inside the information flow of neural nets. Data types and control structures are part of a suitable programming language called NETDEF. Each NETDEF program has a specific neural net that computes it. These nets have a strong modular structure and a synchronization mechanism allowing sequential or parallel execution of subnets, despite the massive parallel feature of neural nets. Each instruction denotes an independent neural net. There are constructors for assignment, conditional and loop instructions. Besides the language core, many other features are possible using the same method. |
publishDate |
2003 |
dc.date.none.fl_str_mv |
2003-04-01 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0104-65002003000100005 |
url |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0104-65002003000100005 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
10.1590/S0104-65002003000100005 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
text/html |
dc.publisher.none.fl_str_mv |
Sociedade Brasileira de Computação |
publisher.none.fl_str_mv |
Sociedade Brasileira de Computação |
dc.source.none.fl_str_mv |
Journal of the Brazilian Computer Society v.8 n.3 2003 reponame:Journal of the Brazilian Computer Society instname:Sociedade Brasileira de Computação (SBC) instacron:UFRGS |
instname_str |
Sociedade Brasileira de Computação (SBC) |
instacron_str |
UFRGS |
institution |
UFRGS |
reponame_str |
Journal of the Brazilian Computer Society |
collection |
Journal of the Brazilian Computer Society |
repository.name.fl_str_mv |
Journal of the Brazilian Computer Society - Sociedade Brasileira de Computação (SBC) |
repository.mail.fl_str_mv |
jbcs@icmc.sc.usp.br |
_version_ |
1754734669592526848 |