Please use this identifier to cite or link to this item:
https://scholarbank.nus.edu.sg/handle/10635/239066
DC Field | Value | |
---|---|---|
dc.title | DEEP MULTIPLE INSTANCE LEARNING ON BIOLOGICAL DATA | |
dc.contributor.author | CHRISTOPHER HENDRA | |
dc.date.accessioned | 2023-04-30T18:00:56Z | |
dc.date.available | 2023-04-30T18:00:56Z | |
dc.date.issued | 2022-07-29 | |
dc.identifier.citation | CHRISTOPHER HENDRA (2022-07-29). DEEP MULTIPLE INSTANCE LEARNING ON BIOLOGICAL DATA. ScholarBank@NUS Repository. | |
dc.identifier.uri | https://scholarbank.nus.edu.sg/handle/10635/239066 | |
dc.description.abstract | This thesis provides a study into the implementation of Deep Multiple Instance Learning (MIL) models to problems in biological data, specifically the detection of m6A RNA modification from direct RNA sequencing data and classification of diabetic retinopathy from funduscopic images. The two problem domains demonstrate a structure that MIL can effectively solve and we are going to show in this thesis that the application of Deep MIL models to these two problems solves practical needs that arise naturally from the deployment of machine learning models in the two domains. Our implementation of Deep MIL models solves not only the basic classification problems in the two domains but also the identification of key instances for stoichiometry prediction in RNA modifications as well as the detection of ROIs in diabetic retinopathy classification. | |
dc.language.iso | en | |
dc.subject | Deep Learning, Machine Learning, Multiple Instance Learning, RNA modification, Diabetic Retinopathy | |
dc.type | Thesis | |
dc.contributor.department | INSTITUTE OF DATA SCIENCE | |
dc.contributor.supervisor | Alexandre Hoang Thiery | |
dc.contributor.supervisor | JONATHAN GOKE | |
dc.description.degree | Ph.D | |
dc.description.degreeconferred | DOCTOR OF PHILOSOPHY (NUSGS) | |
dc.identifier.orcid | 0009-0008-1755-9544 | |
Appears in Collections: | Ph.D Theses (Open) |
Show simple item record
Files in This Item:
File | Description | Size | Format | Access Settings | Version | |
---|---|---|---|---|---|---|
HendraC.pdf | 15.15 MB | Adobe PDF | OPEN | None | View/Download |
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.