• JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
 
  Bookmark and Share
 
 
Master's Dissertation
DOI
https://doi.org/10.11606/D.45.1998.tde-20210729-015959
Document
Author
Full name
Rodrigo de Salvo Braz
Institute/School/College
Knowledge Area
Date of Defense
Published
São Paulo, 1997
Supervisor
Title in Portuguese
Alto nível em redes neurais
Keywords in Portuguese
Inteligência Artificial
Abstract in Portuguese
Nesta disertação apresentamos diversos modelos de redes neurais, ou conexionistas, na busca de uma visão unificada destes modelos e de um entendimento de suas capacidades e limitações. Em seguida, esta visão unificada é usada para considerar-se o tratamento de problemas de alto nível por parte destes modelos que, embora tidos como inapropriados a este tipo de problema, possuem características que seriam úteis em seu tratamento, tais como aprendizado com generalização automática e degradação suave. Os principais problemas são identificados, e um modelo conexionista que trata um deles é apresentado
Title in English
not available
Abstract in English
In this dissertation we present several neural or connectionist network models, looking for a unified vision and understanding oftheir capabilities and limitations. Then, this unified vision is used to think about the treatment of high level problems by these models which, although generally thought of as inappropriate for this kind of problems, have several features that could be useful for them, such as learning with automatic generalization and graceful degration. The main problems are identific, and a connectionist model that deals with one of them is presented
 
WARNING - Viewing this document is conditioned on your acceptance of the following terms of use:
This document is only for private use for research and teaching activities. Reproduction for commercial use is forbidden. This rights cover the whole data about this document as well as its contents. Any uses or copies of this document in whole or in part must include the author's name.
BrazRodrigoSalvo.pdf (15.40 Mbytes)
Publishing Date
2021-07-29
 
WARNING: Learn what derived works are clicking here.
All rights of the thesis/dissertation are from the authors
CeTI-SC/STI
Digital Library of Theses and Dissertations of USP. Copyright © 2001-2024. All rights reserved.