• 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.18.2019.tde-29042019-105852
Document
Author
Full name
Veridiana de Fátima Orlandi Gomes
Institute/School/College
Knowledge Area
Date of Defense
Published
São Carlos, 1997
Supervisor
Committee
Tachibana, Wilson Kendy (President)
Farah, Osvaldo Elias
Sacomano, José Benedito
Title in Portuguese
Redes neurais artificiais: uma contribuição ao processo de decisões financeiras e uma aplicação na previsão de insolvência das organizações
Keywords in Portuguese
Administração financeira
Conhecimento
Pesos sinápticos
Processo de aprendizado
Rede neural artificial
Abstract in Portuguese
O presente trabalho aborda os principais conceitos relacionados com as redes neurais artificiais, que são modelos baseados no comportamento do cérebro. As redes neurais artificiais assemelham-se ao cérebro quanto à obtenção do conhecimento através de um processo de aprendizado, e quanto ao uso da força de conexão interneurônio para armazenar o conhecimento, conhecida como peso sináptico. Existem vários modelos de redes neurais artificiais; os principais modelos são abordados neste trabalho. Estes modelos diferem-se quanto à arquitetura e processo de aprendizado. A escolha do processo de aprendizado é influenciada pela tarefa a ser realizada pela rede neural. Cada modelo de rede neural artificial é mais adequado para resolver um determinado tipo de problema. Sugerem-se alguns problemas na área de administração financeira para serem resolvidos pelo uso desta tecnologia, com a especificação de um determinado modelo, e ainda se propõe uma contribuição para um assunto específico na área de administração financeira: o processo de previsão de insolvência das organizações.
Title in English
Artificial neural networks: a contribution to the process of financial decisions and an application in forecasting of the insolvency of organizations
Keywords in English
Artificial neural network
Financial administration
Knowledge
Learning process
Synaptic weigths
Abstract in English
The present work addresses the main concepts related to artificial neural networks, which are models based on brain behavior. Artificial neural networks resemble the brain regarding acquisition of knowledge through a learning process, and regarding the use of interneuron connection strength to storing the knowledge, known as synaptic weight. There are various artificial neural network models, the main models are addressed in this work. These models differ regarding the architecture and learning process. The choice of learning process is influenced by task to be carried out by the neural network. Each artificial neural network model is suitable for solving a determined type of problem. Some problems in the area of financial administration are suggested for resolution by the use of this technology, specifying a determinated model, and yet intend a contribution to a specific subject in the area of financial administration: the process of forecasting of insolvency of organizations.
 
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.
Dissert_Orlandi_VF.pdf (23.21 Mbytes)
Publishing Date
2019-04-29
 
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.