Projects per year
Abstract
The rise of AI methods to make predictions and decisions has led to a pressing need for more explainable artificial intelligence (XAI) methods. One common approach for XAI is to produce a post-hoc explanation, explaining why a black box ML model made a certain prediction. Formal approaches to post-hoc explanations provide succinct reasons for why a prediction was made, as well as why not another prediction was made. But these approaches assume that features are independent and uniformly distributed. While this means that “why” explanations are correct, they may be longer than required. It also means the “why not” explanations may be suspect as the counterexamples they rely on may not be meaningful. In this paper, we show how one can apply background knowledge to give more succinct “why” formal explanations, that are presumably easier to interpret by humans, and give more accurate “why not” explanations. In addition, we show how to use existing rule induction techniques to efficiently extract background information from a dataset.
Original language | English |
---|---|
Title of host publication | Proceedings of the 37th AAAI Conference on Artificial Intelligence |
Editors | Brian Williams, Yiling Chen, Jennifer Neville |
Place of Publication | Washington DC USA |
Publisher | Association for the Advancement of Artificial Intelligence (AAAI) |
Pages | 4123-4131 |
Number of pages | 9 |
ISBN (Electronic) | 9781577358800 |
DOIs | |
Publication status | Published - 2023 |
Event | AAAI Conference on Artificial Intelligence 2023 - Washington, United States of America Duration: 7 Feb 2023 → 14 Feb 2023 Conference number: 37th https://aaai-23.aaai.org (Website) https://ojs.aaai.org/index.php/AAAI/index (Proceedings) |
Publication series
Name | Proceedings of the AAAI Conference on Artificial Intelligence |
---|---|
Publisher | AAAI Press |
Volume | 37 |
ISSN (Print) | 2159-5399 |
ISSN (Electronic) | 2374-3468 |
Conference
Conference | AAAI Conference on Artificial Intelligence 2023 |
---|---|
Abbreviated title | AAAI 2023 |
Country/Territory | United States of America |
City | Washington |
Period | 7/02/23 → 14/02/23 |
Internet address |
|
Projects
- 1 Active
-
ARC Training Centre in Optimisation Technologies, Integrated Methodologies, and Applications (OPTIMA)
Smith-Miles, K., Stuckey, P., Taylor, P. G., Ernst, A., Aickelin, U., Garcia De La Banda Garcia, M., Pearce, A., Wallace, M., Bondell, H., Hyndman, R., Alpcan, T., Thomas, D. A., Anjomshoa, H., Kirley, M. G., Tack, G., Costa, A., Fackrell, M., Zhang, L., Glazebrook, K., Branke, J., O'Sullivan, B., O'Shea, N., Cheah, A., Meehan, A., Wetenhall, P., Bowly, D., Bridge, J., Faka, S., Mareels, I., Coleman, R. A., Crook, J., Liebman, A. & Aleti, A.
Equans Services Australia Pty Limited
23/09/21 → 23/09/26
Project: Research