Work

Understanding and Estimating Domain Complexity Across Domains

Year: 2023

Type: preprint

Abstract: Artificial Intelligence (AI) systems, trained in controlled environments, often struggle in real-world complexities. We propose a general framework for estimating domain complexity across diverse environments, like open-world learning and real-world applications. This framework distinguishes between intrinsic complexity (inherent to the domain) and extrinsic complexity (dependent on the AI agent). By analyzing dimensionality, sparsity, and diversity within these categories, we offer a comprehensive view of domain challenges. This approach enables quantitative predictions of AI difficulty during environment transitions, avoids bias in novel situations, and helps navigate the vast search spaces of open-world domains.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2312.13487

Authors: Doctor, Katarina, Kejriwal, Mayank, Holder, Lawrence, Kildebeck, Eric, Resmini, Emma, Pereyda, Christopher, Steininger, Robert J., Olivença, Daniel V.

Institutions: United States Naval Research Laboratory, University of Southern California, Washington State University, The University of Texas at Dallas

Language: English

Topic: Domain Adaptation and Few-Shot Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W4390136487

Cites: 25

Cited by: 13

Related to: 10