MaAutoEncoder

Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

THIS WEBPAGE IS DEPRECATED - please visit our new website

A comparative study on unsupervised deep learning methods

Thesis by: Nour Eddin Al-Orjany
Advisor: Prof. Nassir Navab
Supervision by: Shadi Albarqouni, Christoph Baur

Abstract

Deep Learning has been growing in popularity in the last years due to its outstanding performance on high dimensional data, being capable of establishing complex mappings between input and output. New techniques and network architectures are evolving both in the supervised and unsupervised deep learning domains. In this work, an overview on some of the recent successful techniques in unsupervised deep learning will be given. The focus in this work primarily lies on how such methods capture the underlying structure of complex input data. In particular, recent developments such as Autoencoders, Variational and Adversarial Autoencoders or Generative Adversarial Networks will be investigated. Through this survey study, a practical explanation on how and when to use these techniques will be derived. Different techniques are compared against each other, finding their strengths and weaknesses and giving concrete examples by applying theses techniques to publicly available datasets, i.e. MNIST, CIFAR and some medical datasets.

Literature

Resultant Paper


ProjectForm
Title: A comparative study on unsupervised deep learning methods
Abstract: Deep Learning has been growing in popularity in the last years due to its outstanding performance on high dimensional data, being capable of establishing complex mappings between input and output. New techniques and network architectures are evolving both in the supervised and unsupervised deep learning domains. In this work, an overview on some of the recent successful techniques in unsupervised deep learning will be given. The focus in this work primarily lies on how such methods capture the underlying structure of complex input data. In particular, recent developments such as Autoencoders, Variational and Adversarial Autoencoders or Generative Adversarial Networks will be investigated. Through this survey study, a practical explanation on how and when to use these techniques will be derived. Different techniques are compared against each other, finding their strengths and weaknesses and giving concrete examples by applying theses techniques to publicly available datasets, i.e. MNIST, CIFAR and some medical datasets.
Student: Nour Eddin Al-Orjany
Director: Prof. Nassir Navab
Supervisor: Shadi Albarqouni, Christoph Baur
Type: DA/MA/BA
Area:  
Status: finished
Start:  
Finish:  
Thesis (optional):  
Picture:  


Edit | Attach | Refresh | Diffs | More | Revision r1.4 - 18 Aug 2017 - 09:58 - ShadiAlbarqouni