Camburu, Oana-Maria;
(2020)
Explaining Deep Neural Networks.
Doctoral thesis (Ph.D), University of Oxford.
Preview |
Text
thesis.pdf - Published Version Download (1MB) | Preview |
Abstract
Deep neural networks are becoming more and more popular due to their revolutionary success in diverse areas, such as computer vision, natural language processing, and speech recognition. However, the decision-making processes of these models are generally not interpretable to users. In various domains, such as healthcare, finance, or law, it is critical to know the reasons behind a decision made by an artificial intelligence system. Therefore, several directions for explaining neural models have recently been explored. In this thesis, I investigate two major directions for explaining deep neural networks. The first direction consists of feature-based post-hoc explanatory methods, that is, methods that aim to explain an already trained and fixed model (post-hoc), and that provide explanations in terms of input features, such as tokens for text and superpixels for images (feature-based). The second direction consists of self-explanatory neural models that generate natural language explanations, that is, models that have a built-in module that generates explanations for the predictions of the model.
| Type: | Thesis (Doctoral) |
|---|---|
| Qualification: | Ph.D |
| Title: | Explaining Deep Neural Networks |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.48550/arXiv.2010.01496 |
| Publisher version: | https://doi.org/10.48550/arXiv.2010.01496 |
| Language: | English |
| Additional information: | This version is the version of record. For information on re-use, please refer to the publisher's terms and conditions. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10184051 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
