Title:
Combining Classification and Clustering Tasks to Categorize Known and Unknown Classes

Thumbnail Image
Authors
Shabbir, Javeria
Authors
Advisors
Kira, Zsolt
Advisors
Associated Organizations
Organizational Unit
Series
Supplementary to
Abstract
Since the past few years research has been directed towards the training of neural networks using unlabeled data or pairwise pseudo constraints known as unsupervised learning and semi-supervised learning respectively. In this thesis, we explored several methods to improve the performance of the current state-of-the-art algorithm for unsupervised learning called SCAN using semi-supervision from pairwise pseudo constraints.
Sponsor
Date Issued
2022-12-19
Extent
Resource Type
Text
Resource Subtype
Thesis
Rights Statement
Rights URI