1 / 27

S istemas I nteligentes Santiago Aja Fernández sanaja@tel.uva.es

Departamento de Teoría de la Señal, Comunicaciones e Ingeniería Telemática. CURSO DE DOCTORADO. S istemas I nteligentes Santiago Aja Fernández sanaja@tel.uva.es http://www.lpi.tel.uva.es/~santi/fuzzy/. Sistemas Inteligentes. E squema de la A signatura. 1. Introducción a la asignatura

austin-chaney
Télécharger la présentation

S istemas I nteligentes Santiago Aja Fernández sanaja@tel.uva.es

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Departamento de Teoría de la Señal, Comunicaciones e Ingeniería Telemática CURSO DE DOCTORADO SistemasInteligentes Santiago Aja Fernández sanaja@tel.uva.es http://www.lpi.tel.uva.es/~santi/fuzzy/

  2. Sistemas Inteligentes Esquema de la Asignatura 1. Introducción a la asignatura - Reconocimiento de Patrones - Lógica difusa 2. Reconocimiento de Patrones 3. Lógica Difusa (Fuzzy Logic) 4. Prácticas 2

  3. Sistemas Inteligentes Posible definición de Patrón: “As opposite of a chaos; it is an entity, vaguely defined, that could be given a name” (Watanabe) “A form, template or model which can be used to make or to generate things or parts of a thing, especially if the things that are generated have enough in common for the underlying pattern to be inferred or discerned, in which case the things are said to exhibit the pattern.” (wikipedia.org) 3

  4. Sistemas Inteligentes 4

  5. Sistemas Inteligentes • ¿Reconocimiento? • Recuperación de la información (Asociación). Memoria asociativa perfecta (Pattern Matching) • Información incompleta (Memoria Asociativa) • Agrupamiento (Clustering) • Etiquetado (Labeling) • (Aprendizaje) 5

  6. Árbol Sistemas Inteligentes Comportamiento humano 6

  7. 010111010 101010000 001010101 010111101 010000101 Sistemas Inteligentes Análisis automático 7

  8. Sistemas Inteligentes PROBLEMA: ¡¡¡Los patrones se encuentran solapados!!!! 8

  9. Sistemas Inteligentes Relación con otras áreas Inteligencia Artificial (IA); Muy asociado al concepto de símbolo IA Trabaja con símbolos, que se procesan de manera diferente que los números. Rama de IA: CWW (computing with words) 9

  10. Sistemas Inteligentes 10

  11. Sistemas Inteligentes Reconocimiento de patrones “Pattern recognition is the scientific discipline whose goal is the classification of objects into a number of categories or classes.[…] PR is an integral part in the most machine intelligence systems built for decision making.” (Theodoridis y Koutroumbas) Otras definiciones: http://en.wikipedia.org/wiki/Pattern_recognition 11

  12. Sistemas Inteligentes • ¿Cómo se trabaja? • Los patrones están definidos mediante características (features) • Los patrones en los que queremos clasificar se denominan clases. • Una clase se define en un espacio n-dimensional de características 12

  13. Sistemas Inteligentes Ejemplo “Sorting incoming Fish on a conveyor according to species using optical sensing” Sea bass (lubina) Species Salmon (salmón) 13

  14. Sistemas Inteligentes • Problem Analysis • Set up a camera and take some sample images to extract features • Length • Lightness • Width • Number and shape of fins • Position of the mouth, etc… This is the set of all suggested features to explore for use in our classifier! 14

  15. Sistemas Inteligentes • Preprocessing • Use a segmentation operation to isolate fishes from one another and from the background • Information from a single fish is sent to a feature extractor whose purpose is to reduce the data by measuring certain features • The features are passed to a classifier 15

  16. Sistemas Inteligentes 16

  17. Sistemas Inteligentes • Classification Select the length of the fish as a possible feature for discrimination 17

  18. Sistemas Inteligentes The length is a poor feature alone! Select the lightness as a possible feature. 18

  19. Sistemas Inteligentes 19

  20. Sistemas Inteligentes • Threshold decision boundary and cost relationship • Move our decision boundary toward smaller values of lightness in order to minimize the cost (reduce the number of sea bass that are classified salmon!) Task of decision theory 20

  21. Sistemas Inteligentes • Adopt the lightness and add the width of the fish Fish x = [x1, x2] Lightness Width 21

  22. Sistemas Inteligentes 22

  23. Sistemas Inteligentes • We might add other features that are not correlated with the ones we already have. A precaution should be taken not to reduce the performance by adding such “noisy features” • Ideally, the best decision boundary should be the one which provides an optimal performance such as in the following figure: 23

  24. Sistemas Inteligentes 24

  25. Sistemas Inteligentes • However, our satisfaction is premature because the central aim of designing a classifier is to correctly classify novel input Issue of generalization! 25

  26. Sistemas Inteligentes 26

  27. Sistemas Inteligentes Lógica Borrosa (Fuzzy Logic) 27

More Related