• 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.45.2000.tde-20210729-115619
Document
Author
Full name
Maurício Bellissimo Falleiros
E-mail
Institute/School/College
Knowledge Area
Date of Defense
Published
São Paulo, 2000
Supervisor
Title in Portuguese
Análise formal do aprendizado supervisionado por árvores de decisão
Keywords in Portuguese
Aprendizado Computacional
Inteligência Artificial
Abstract in Portuguese
Nesta dissertação apresentamos duas vertentes da pesquisa em aprendizagem computacional, uma formal e outra empírica, destacando o modelo de análise 'Provavelmente Aproximadamente Correto' (PAC) e o algoritmo REAL de indução de árvores de decisãosobre atributos de domínio real. A seguir, levantamos a curva de aprendizagem do algoritmo REAL sobre uma base de dados padrão para testes de algoritmos de aprendizagem desta natureza e comparamos esta curva com as previsões teóricas dadas pelomodelo PAC e pelo modelo de Convergência Uniforme. Fica evidente a grande lacuna entre estes resultados e então propomos algumas possibilidades de aprofundamento deste análise
Title in English
not available
Abstract in English
In this dissertation we present two frameworks of the machine learning research, one formal and the other practical, emphasizing the analysis model 'Probably Approximately Correct' (PAC) and the algorithm REAL of induction of decision trees onreal-valued attributes. We then build the learning curve of the algorithm REAL on a standard database for benchmarking learning algorithms of this nature and compare this curve and the theoretical predictions given by the PAC model and by theUniform Convergence model. The gap between these claar and then we propose some possibilities for a deeper approach
 
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.
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.