Continuous States Conditional Random Fields Training Using Adaptive Integration

DSpace/Manakin Repository

Open Research Exeter (ORE)

Continuous States Conditional Random Fields Training Using Adaptive Integration

Show simple item record

dc.contributor.author Leitao, Joao en_US
dc.date.accessioned 2011-05-23T16:36:18Z en_US
dc.date.accessioned 2013-03-21T10:37:04Z
dc.date.issued 2010-12-17 en_US
dc.description.abstract The extension of Conditional Random Fields (CRF) from discrete states to continuous states will help remove the limitation of the number of states and allow new applications for CRF. In this work, our attempts to obtain a correct procedure to train continuous state conditional random fields through maximum likelihood are presented. By deducing the equations governing the extension of the CRF to continuous states it was possible to merge with the Particle Filter (PF) concept to obtain a formulation governing the training of continuous states CRFs by using particle filters. The results obtained indicated that this process is unsuitable because of the low convergence of the PF integration rate in the needed integrations replacing the summation in CRFs. So a change in concept to an adaptive integration scheme was made. Based on an extension of the Binary Space Partition (BSP) algorithm an adaptive integration process was devised with the aim of producing a more precise integration while retaining a less costly function evaluation than PF. This allowed us to train continuous states conditional random fields with some success. To verify the possibility of increasing the dimension of the states as a vector of continuous states a scalable version was also used to briefly assess its fitness in two-dimensions with quadtrees. This is an asymmetric two-dimensional space partition scheme. In order to increase the knowledge of the problem it would be interesting to have further information of the relevant features. A feature selection embedded method was used based on the lasso regulariser with the intention of pinpointing the most relevant feature functions indicating the relevant features. en_GB
dc.description.sponsorship Motorola en_GB
dc.description.sponsorship EPSRC en_GB
dc.identifier.grantnumber EP 4/C 5376614/1 en_GB
dc.identifier.uri http://hdl.handle.net/10036/3095 en_US
dc.language.iso en en_GB
dc.publisher University of Exeter en_GB
dc.subject Conditional Random Fields en_GB
dc.subject Adaptive Integration en_GB
dc.subject Quadtrees en_GB
dc.subject Particle Filters en_GB
dc.title Continuous States Conditional Random Fields Training Using Adaptive Integration en_GB
dc.type Thesis or dissertation en_GB
dc.date.available 2011-05-23T16:36:18Z en_US
dc.date.available 2013-03-21T10:37:04Z
dc.contributor.advisor Everson, Richard en_US
dc.publisher.department College of Engineering, Mathematics and Physical Sciences en_GB
dc.type.degreetitle PhD in Computer Science en_GB
dc.type.qualificationlevel Doctoral en_GB
dc.type.qualificationname PhD en_GB


Files in this item

Files Size Format View Description
LeitaoJ.pdf 1.215Mb PDF View/Open Thesis
LeitaoJ_fm.pdf 155.0Kb PDF View/Open Front matter

This item appears in the following Collection(s)

Show simple item record

Browse

My Account

Local Links