MaSSAL

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

Semi-supervised Active Learning

Supervision: Prof. Dr. Nassir Navab, Dr. Seong Tae Kim

Abstract

Deep neural network training generally requires a large dataset of labeled data points. In practice, large sets of unlabeled data are usually available, but acquiring labels for these datasets is time-consuming and expensive. Active Learning (AL) is a training protocol that aims at minimizing labeling effort in machine learning applications. Active learning algorithms try to sequentially query labels for the most informative data points of an unlabeled data set. Semi-supervised learning (SSL) is a method that uses unlabeled data for model training in order to improve performance. In this thesis, we will explore the combination of these two promising approaches for the efficient training of deep neural networks. In particular, we explore how query selection criteria of AL algorithms have to be designed when used in conjunction with SSL algorithms.

Requirements:

  • Good understanding of statistics and machine learning methods.
  • Very good programming skills in Python & TensorFlow? / PyTorch?

Location:

  • Garching


ProjectForm
Title: Semi-supervised Active Learning
Abstract: Deep neural network training generally requires a large dataset of labeled data points. In practice, large sets of unlabeled data are usually available, but acquiring labels for these datasets is time-consuming and expensive. Active Learning (AL) is a training protocol that aims at minimizing labeling effort in machine learning applications. Active learning algorithms try to sequentially query labels for the most informative data points of an unlabeled data set. Semi-supervised learning (SSL) is a method that uses unlabeled data for model training in order to improve performance. In this thesis, we will explore the combination of these two promising approaches for the efficient training of deep neural networks. In particular, we explore how query selection criteria of AL algorithms have to be designed when used in conjunction with SSL algorithms.
Student: Felix Buchert
Director: Prof. Dr. Nassir Navab
Supervisor: Dr. Seong Tae Kim
Type: Master Thesis
Area: Machine Learning
Status: running
Start:  
Finish:  
Thesis (optional):  
Picture:  


Edit | Attach | Refresh | Diffs | More | Revision r1.1 - 23 Sep 2020 - 10:02 - SeongTaeKim