https://github.com/hasnep/dissertation
🎓 My Master's dissertation on interpretable machine learning
https://github.com/hasnep/dissertation
dissertation gaussian-processes machine-learning
Last synced: 8 months ago
JSON representation
🎓 My Master's dissertation on interpretable machine learning
- Host: GitHub
- URL: https://github.com/hasnep/dissertation
- Owner: Hasnep
- Created: 2019-03-30T15:41:47.000Z (about 7 years ago)
- Default Branch: master
- Last Pushed: 2020-08-02T17:50:00.000Z (almost 6 years ago)
- Last Synced: 2025-01-21T09:27:30.468Z (over 1 year ago)
- Topics: dissertation, gaussian-processes, machine-learning
- Language: TeX
- Homepage: https://ha.nnes.dev/projects/dissertation
- Size: 5.96 MB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Dissertation
My dissertation for my master's in maths at the University of Exeter, titled "Can statistics help us to understand deep learning?"
## Abstract
> Machine learning and deep neural networks have seen widespread success in many of modern life — sometimes visibly, as with driverless cars, but in some cases more discreetly, such as the use of machine learning algorithms in the U.S. judicial system.
> Due to their hierarchical structure, deep neural networks are a ‘black box’ which no human can understand, which could cause problems when a machine learning algorithm does something unforeseen.
> Statistical methods such as Gaussian processes may offer a way to look inside this black box, as they offer a similar flexibility and wide range of uses, and are much more easily interpreted by humans.
> In this project, a simple non-linear function was used to train a deep neural network and then multiple regression and Gaussian processes were used to model the output of the neural network.
> Regularisation methods such as LASSO were used to reduce the regression model to a more human understandable form, which was then used as the mean function of a Gaussian process to further improve the fit of the model.
## Download
| [Final report](https://github.com/Hasnep/dissertation/raw/master/dissertation/dissertation.pdf) | [Literature Review](https://github.com/Hasnep/dissertation/raw/master/literaturereview/literaturereview.pdf) | [Poster](https://github.com/Hasnep/dissertation/raw/master/poster/poster.pdf) | [Presentation](https://github.com/Hasnep/dissertation/raw/master/presentation/presentation.pdf) |
| :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
| [](https://github.com/Hasnep/dissertation/raw/master/dissertation/dissertation.pdf) | [](https://github.com/Hasnep/dissertation/raw/master/literaturereview/literaturereview.pdf) | [](https://github.com/Hasnep/dissertation/raw/master/poster/poster.pdf) | [](https://github.com/Hasnep/dissertation/raw/master/presentation/presentation.pdf) |