Data Efficient Algorithms and Interpretability Requirements for Personalized Assessment of Taskable AI Systems
Abstract
The vast diversity of internal designs of black-box AI systems and their nuanced zones of safe functionality make it difficult for a layperson to use them without unintended side effects. The focus of my dissertation is to develop algorithms and requirements of interpretability that would enable a user to assess and understand the limits of an AI system's safe operability. We develop an assessment module that lets an AI system execute high-level instruction sequences in simulators and answer the user queries about its execution of sequences of actions. Our results show that such a primitive query-response capability is sufficient to efficiently derive a user-interpretable model of the system in stationary, fully observable, and deterministic settings.
Cite
Text
Verma. "Data Efficient Algorithms and Interpretability Requirements for Personalized Assessment of Taskable AI Systems." International Joint Conference on Artificial Intelligence, 2021. doi:10.24963/IJCAI.2021/693Markdown
[Verma. "Data Efficient Algorithms and Interpretability Requirements for Personalized Assessment of Taskable AI Systems." International Joint Conference on Artificial Intelligence, 2021.](https://mlanthology.org/ijcai/2021/verma2021ijcai-data/) doi:10.24963/IJCAI.2021/693BibTeX
@inproceedings{verma2021ijcai-data,
title = {{Data Efficient Algorithms and Interpretability Requirements for Personalized Assessment of Taskable AI Systems}},
author = {Verma, Pulkit},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2021},
pages = {4923-4924},
doi = {10.24963/IJCAI.2021/693},
url = {https://mlanthology.org/ijcai/2021/verma2021ijcai-data/}
}