Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
The Removal of False Signals from Convolutional Neural Networks
Thesis (PhD)--Stellenbosch University, 2026.
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
Stellenbosch : Stellenbosch University
2026
|
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867613922950905856 |
|---|---|
| access_status_str | Open Access |
| author | Burger, Leon Eldon |
| author2 | Engelbrecht, A. P. |
| author_browse | Burger, Leon Eldon Engelbrecht, A. P. |
| author_facet | Engelbrecht, A. P. Burger, Leon Eldon |
| author_sort | Burger, Leon Eldon |
| collection | Thesis |
| dc_rights_str_mv | Stellenbosch University |
| description | Thesis (PhD)--Stellenbosch University, 2026. |
| format | Thesis |
| id | oai:scholar.sun.ac.za:10019.1/135655 |
| institution | Stellenbosch University (South Africa) |
| language | English |
| last_indexed | 2026-06-10T12:43:50.825Z |
| license_str | Other — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from SUNScholar — Stellenbosch University Repository |
| publishDate | 2026 |
| publishDateRange | 2026 |
| publishDateSort | 2026 |
| publisher | Stellenbosch : Stellenbosch University |
| publisherStr | Stellenbosch : Stellenbosch University |
| record_format | dspace |
| source_str | SUNScholar — Stellenbosch University Repository |
| spelling | oai:scholar.sun.ac.za:10019.1/135655 The Removal of False Signals from Convolutional Neural Networks Burger, Leon Eldon Engelbrecht, A. P. Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering. Thesis (PhD)--Stellenbosch University, 2026. Burger, L. E. 2026. The Removal of False Signals from Convolutional Neural Networks. Unpublished doctoral dissertation. Stellenbosch: Stellenbosch University [online]. Available: https://scholar.sun.ac.za/items/760a798b-c924-412a-9b44-da5aefe4a79e Convolutional neural networks have achieved performance comparable to human experts in various computer vision tasks. However, despite this comparable performance, the decision-making process differs significantly between convolutional neural networks and human experts. Whereas human decisions are guided by causal inference, convolutional neural networks rely on associations that may not reflect causal relationships. When the decision of a convolutional neural network is based on false associations, learned from confounding features in the training data, the model will produce incorrect predictions when the false associations do not hold. To prevent failures in critical domains such as healthcare, false relationships must be identified and removed. This dissertation critically evaluates, compares and improves methods to identify and remove false associations from convolutional neural networks. A taxonomy of common confounding features is introduced along with a second taxonomy that categorises confounders by their key characteristics, to support the principled selection of appropriate removal strategies. A general evaluation framework is further developed to quantify the effectiveness of con-founder removal methods across a wide range of confounding features. The framework is applied to both established and newly proposed methods which allowed the relative effectiveness of confounding removal methods to be established. The results highlight significant variation in method effectiveness, demonstrate practical shortcomings of current methods, and show that targeted refinements can yield measurable improvements. Overall, the dissertation provides a structured foundation for the development and reliable evaluation of confounder robust convolutional neural networks. Doctoral 2026-04-07T09:01:36Z 2026-04-07T09:01:36Z 2026-03 Thesis https://scholar.sun.ac.za/handle/10019.1/135655 en Stellenbosch University 142 pages : ill. application/pdf Stellenbosch : Stellenbosch University |
| spellingShingle | Burger, Leon Eldon The Removal of False Signals from Convolutional Neural Networks |
| title | The Removal of False Signals from Convolutional Neural Networks |
| title_full | The Removal of False Signals from Convolutional Neural Networks |
| title_fullStr | The Removal of False Signals from Convolutional Neural Networks |
| title_full_unstemmed | The Removal of False Signals from Convolutional Neural Networks |
| title_short | The Removal of False Signals from Convolutional Neural Networks |
| title_sort | removal of false signals from convolutional neural networks |
| url | https://scholar.sun.ac.za/handle/10019.1/135655 |
| work_keys_str_mv | AT burgerleoneldon theremovaloffalsesignalsfromconvolutionalneuralnetworks AT burgerleoneldon removaloffalsesignalsfromconvolutionalneuralnetworks |