TechRxiv
UCC-DS-2020.pdf (374.92 kB)

Explaining probabilistic Artificial Intelligence (AI) models by discretizing Deep Neural Networks

Download (374.92 kB)
preprint
posted on 18.06.2021, 15:55 by Rabia Saleem, Bo Yuan, Fatih Kurugollu, Ashiq Anjum
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 decision- making 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.

History

Email Address of Submitting Author

r.saleem3@unimail.derby.ac.uk

ORCID of Submitting Author

https://orcid.org/0000-0002-9223-6752

Submitting Author's Institution

University of Derby

Submitting Author's Country

United Kingdom

Usage metrics

Licence

Exports