A framework for interactive training of automatic image analysis models based on learned image representations, active learning, and visualization techniques

Abstract. In this thesis work, the problem of applying active learning for a label efficient training of deep learning models is addressed. Firstly, in chapter one, the problem is introduced as well as the objectives and results of this thesis work. In chapter 2, a state of the art of active learnin...

Full description

Autores:
Otálora Montenegro, Juan Sebastian
Tipo de recurso:
Fecha de publicación:
2016
Institución:
Universidad Nacional de Colombia
Repositorio:
Universidad Nacional de Colombia
Idioma:
spa
OAI Identifier:
oai:repositorio.unal.edu.co:unal/59995
Acceso en línea:
https://repositorio.unal.edu.co/handle/unal/59995
http://bdigital.unal.edu.co/57883/
Palabra clave:
51 Matemáticas / Mathematics
6 Tecnología (ciencias aplicadas) / Technology
62 Ingeniería y operaciones afines / Engineering
Deep Learning
Machine Learning
Eye Fundus imaging
Active Learning
Medical Imaging
Expected Gradient Length
On-line Learning
Aprendizaje de máquina
Redes Neuronales Profundas
Aprendizaje Activo
Aprendizaje de la Representación
Análisis de Imágenes Médicas
Aprendizaje en Linea
Longitud esperada del gradiente
Rights
openAccess
License
Atribución-NoComercial 4.0 Internacional