Explaining probabilistic Artificial Intelligence (AI) models by discretizing Deep Neural Networks
Conference item
Authors | Saleem, Rabia, Yuan, Bo, Kurugollu, Fatih and Anjum, Ashiq |
---|---|
Abstract | Artificial Intelligence (AI) models can learn from data and make decisions without any human intervention. However, the deployment of such models is challenging and risky because we do not know how the internal decisionmaking is happening in these models. Especially, the high-risk decisions such as medical diagnosis or automated navigation demand explainability and verification of the decision making process in AI algorithms. This research paper aims to explain Artificial Intelligence (AI) models by discretizing the black-box process model of deep neural networks using partial differential equations. The PDEs based deterministic models would minimize the time and computational cost of the decision-making process and reduce the chances of uncertainty that make the prediction more trustworthy. |
Keywords | Artificial Intelligence; Deep Neural Networks; Partial differential equations; Discretization |
Year | 2020 |
Journal | 2020 IEEE/ACM 13th International Conference on Utility and Cloud Computing (UCC) |
2020 IEEE/ACM 13th International Conference on Utility and Cloud Computing (UCC) | |
Publisher | IEEE |
Digital Object Identifier (DOI) | https://doi.org/10.1109/ucc48980.2020.00070 |
Web address (URL) | http://hdl.handle.net/10545/625606 |
http://creativecommons.org/licenses/by-nc-sa/4.0/ | |
hdl:10545/625606 | |
ISBN | 9780738123943 |
File | File Access Level Open |
File | File Access Level Open |
Publication dates | 30 Dec 2020 |
Publication process dates | |
Deposited | 08 Feb 2021, 15:50 |
Accepted | 30 Oct 2020 |
Rights | Attribution-NonCommercial-ShareAlike 4.0 International |
Contributors | University of Derby and University of Leicester |
https://repository.derby.ac.uk/item/9269v/explaining-probabilistic-artificial-intelligence-ai-models-by-discretizing-deep-neural-networks
Download files
152
total views0
total downloads0
views this month0
downloads this month