Banca de QUALIFICAÇÃO: JUSCELINO PEREIRA DE ARAÚJO

Uma banca de QUALIFICAÇÃO de MESTRADO foi cadastrada pelo programa.
DISCENTE : JUSCELINO PEREIRA DE ARAÚJO
DATA : 12/06/2018
HORA: 10:00
LOCAL: Auditório do CCET
TÍTULO:

Analysis of Rate of Convergence of k-Nearest Neighbors Classification Rule

PALAVRAS-CHAVES:

k-Nearest Neighbor rule; Classification rules; Rates of convergence; Binary classification

PÁGINAS: 45
GRANDE ÁREA: Ciências Exatas e da Terra
ÁREA: Matemática
RESUMO:

The main objective of this work is to analyze the velocity of convergence of k-Nearest Neighbor (kNN) classification rule. Thus the binary classification problem is approached. The main theoretical results are developed, overall Stone Theorem, which guarantees the universal consistency of classification rules with some properties. Specifically the kNN rule is analyzed, mainly its universal consistency. Then restrictive conditions which allow uniform rates of convergence for a family of distributions are presented. Finally, under the mentioned restrictive conditions the order of magnitude of rate of convergence of kNN rule is obtained such that it cross out the need of a bounded space of observations.

MEMBROS DA BANCA:
Externo ao Programa - 2579664 - ALLAN DE MEDEIROS MARTINS
Interno - 1153898 - ANDRE GUSTAVO CAMPOS PEREIRA
Interno - 1217007 - ANDRE LUIS SANTOS DE PINHO
Presidente - 2193700 - ROBERTO TEODORO GURGEL DE OLIVEIRA