Pattern recognition via projection–based k–NN rules
"We introduce a new procedure for pattern recognition, based on the concepts of random projections and nearest neighbors. It can be thought as an improvement of the classical nearest neighbors classification rules. Besides the concept of neighbors we introduce the notion of district, a larger s...
Guardado en:
| Autor principal: | |
|---|---|
| Autor Corporativo: | |
| Otros Autores: | , |
| Formato: | Libro electrónico |
| Lenguaje: | Inglés |
| Publicado: |
Victoria, Pcia. de Buenos Aires :
Universidad de San Andrés,
[2008].
|
| Colección: | Documento de trabajo (Universidad de San Andrés. Departamento de Matemática y Ciencias) ;
53 |
| Materias: | |
| Acceso en línea: | http://hdl.handle.net/10908/553 |
| Aporte de: | Registro referencial: Solicitar el recurso aquí |
| LEADER | 01971nam a22003254a 4500 | ||
|---|---|---|---|
| 001 | 990000577140204151 | ||
| 005 | 20220315145806.0 | ||
| 006 | m d | ||
| 007 | cr#cn######### | ||
| 008 | 110919s2008 ag sb 000 0 eng d | ||
| 035 | |a (udesa)000057714USA01 | ||
| 099 | |a Recurso electrónico en INTERNET | ||
| 100 | 1 | |a Fraiman, Ricardo. | |
| 245 | 1 | 0 | |a Pattern recognition via projection–based k–NN rules |h [recurso electrónico] / |c Ricardo Fraiman, Ana Justel y Marcela Svarc. |
| 260 | |a Victoria, Pcia. de Buenos Aires : |b Universidad de San Andrés, |c [2008]. | ||
| 490 | 1 | |a Documento de trabajo ; |v 53 | |
| 516 | |a Texto en PDF | ||
| 500 | |a Título tomado de la pantalla de presentación (visto 19 de septiembre de 2011). | ||
| 500 | |a Junio 2008". | ||
| 538 | |a Modo de acceso: World Wide Web. | ||
| 504 | |a Incluye referencias bibliográficas. | ||
| 520 | |a "We introduce a new procedure for pattern recognition, based on the concepts of random projections and nearest neighbors. It can be thought as an improvement of the classical nearest neighbors classification rules. Besides the concept of neighbors we introduce the notion of district, a larger set which will be projected. Then we apply one dimensional k-NN methods to the projected data on randomly selected directions. In this way we are able to provide a method with some robustness properties and more accurate to handle high dimensional data. The procedure is also universally consistent. We challenge the method with the Isolet data where we obtain a very high classification score." | ||
| 650 | 0 | |a Multivariate analysis. | |
| 650 | 0 | |a Robust statistics. | |
| 650 | 0 | |a Pattern perception. | |
| 700 | 1 | |a Svarc, Marcela. | |
| 700 | 1 | |a Justel, Ana. | |
| 710 | 2 | |a Universidad de San Andrés. |b Departamento de Matemática y Ciencias. | |
| 830 | 0 | |a Documento de trabajo (Universidad de San Andrés. Departamento de Matemática y Ciencias) ; |v 53 | |
| 856 | 4 | 0 | |u http://hdl.handle.net/10908/553 |