Data Efficient Algorithms and Interpretability Requirements for Personalized Assessment of Taskable AI Systems

Verma, Pulkit

doi:10.24963/ijcai.2021/693

Data Efficient Algorithms and Interpretability Requirements for Personalized Assessment of Taskable AI Systems

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Doctoral Consortium. Pages 4923-4924.

https://doi.org/10.24963/ijcai.2021/693

Keywords

Knowledge Representation and Reasoning: Action, Change and Causality
Planning and Scheduling: Model-Based Reasoning

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.

Pulkit Verma. 2021. Data Efficient Algorithms and Interpretability Requirements for Personalized Assessment of Taskable AI Systems. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 4923–4924. https://doi.org/10.24963/ijcai.2021/693

@inproceedings{ijcai2021p693,
  title     = {Data Efficient Algorithms and Interpretability Requirements for Personalized Assessment of Taskable AI Systems},
  author    = {Verma, Pulkit},
  booktitle = {Proceedings of the Thirtieth International Joint Conference on
               Artificial Intelligence, {IJCAI-21}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Prof. Zhi-Hua Zhou},
  pages     = {4923--4924},
  year      = {2021},
  month     = {8},
  note      = {Doctoral Consortium},
  doi       = {10.24963/ijcai.2021/693},
  url       = {https://doi.org/10.24963/ijcai.2021/693},
}

TY  - CPAPER
TI  - Data Efficient Algorithms and Interpretability Requirements for Personalized Assessment of Taskable AI Systems
AU  - Verma, Pulkit
T2  - Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2021
SP  - 4923
EP  - 4924
DO  - 10.24963/ijcai.2021/693
UR  - https://doi.org/10.24963/ijcai.2021/693
ER  -