Skip to main content

Comparing Explanations between Random Forests and Artificial Neural Networks

Harris, Lee, Grzes, Marek (2019) Comparing Explanations between Random Forests and Artificial Neural Networks. In: Proceedings of the 2019 IEEE International Conference on Systems, Man, and Cybernetics (IEEE SMC). . IEEE (doi:10.1109/SMC.2019.8914321)

PDF - Author's Accepted Manuscript
Download (464kB) Preview
[img]
Preview
Official URL
http://dx.doi.org/10.1109/SMC.2019.8914321

Abstract

The decisions made by machines are increasingly comparable in predictive performance to those made by humans, but these decision making processes are often concealed as black boxes. Additional techniques are required to extract understanding, and one such category are explanation methods. This research compares the explanations of two popular forms of artificial intelligence; neural networks and random forests. Researchers in either field often have divided opinions on transparency, and comparing explanations may discover similar ground truths between models. Similarity can help to encourage trust in predictive accuracy alongside transparent structure and unite the respective research fields. This research explores a variety of simulated and real-world datasets that ensure fair applicability to both learning algorithms. A new heuristic explanation method that extends an existing technique is introduced, and our results show that this is somewhat similar to the other methods examined whilst also offering an alternative perspective towards least-important features.

Item Type: Conference or workshop item (Proceeding)
DOI/Identification number: 10.1109/SMC.2019.8914321
Uncontrolled keywords: Random forests, neural networks, transparent AI, interpretability, explainability
Subjects: Q Science > QA Mathematics (inc Computing science) > QA 76 Software, computer programming, > QA76.87 Neural computers, neural networks
Divisions: Faculties > Sciences > School of Computing > Computational Intelligence Group
Depositing User: Marek Grzes
Date Deposited: 19 Jul 2019 15:31 UTC
Last Modified: 16 Jan 2020 16:36 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/75472 (The current URI for this page, for reference purposes)
  • Depositors only (login required):

Downloads

Downloads per month over past year