Please use this identifier to cite or link to this item: https://hdl.handle.net/11147/9976
Title: Improved quasi-supervised learning by expectation-maximization
Authors: Karaçalı, Bilge
Keywords: quasi-supervised learning
expectation-maximization
constant false alarm rate
maximum a posteriori rule
Issue Date: 2013
Publisher: Institute of Electrical and Electronics Engineers Inc.
Series/Report no.: Signal Processing and Communications Applications Conference
Abstract: In this paper, a new statistical learning method was developed that implements the quasi-supervised learning method in an expectation-maximization loop. First, automatic strategies were generated that separated the samples drawn from different distributions into respective sample sets using the posterior probabilities computed via quasi-supervised learning based on partially separated samples. An expectation-maximization loop was then constructed by combining this procedure with the posterior probability computation step using the new separated sample sets. In controlled experiments on recognition problems with varying difficulties, the proposed method was observed to consistently outperform the plain quasi-supervised learning method.
Description: 21st Signal Processing and Communications Applications Conference (SIU)
URI: https://hdl.handle.net/11147/9976
ISBN: 978-1-4673-5563-6
978-1-4673-5562-9
ISSN: 2165-0608
Appears in Collections:WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection

Show full item record

CORE Recommender

Page view(s)

46
checked on Aug 15, 2022

Google ScholarTM

Check

Altmetric


Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.