A Definition and a Test for Human-Level Artificial Intelligence
Artificial Intelligence
2022-12-16 v5 Computation and Language
Abstract
Despite recent advances of AI research in many application-specific domains, we do not know how to build a human-level artificial intelligence (HLAI). We conjecture that learning from others' experience with the language is the essential characteristic that distinguishes human intelligence from the rest. Humans can update the action-value function with the verbal description as if they experience states, actions, and corresponding rewards sequences firsthand. In this paper, we present a classification of intelligence according to how individual agents learn and propose a definition and a test for HLAI. The main idea is that language acquisition without explicit rewards can be a sufficient test for HLAI.
Cite
@article{arxiv.2011.09410,
title = {A Definition and a Test for Human-Level Artificial Intelligence},
author = {Deokgun Park and Md Ashaduzzaman Rubel Mondol and Aishwarya Pothula and Mazharul Islam},
journal= {arXiv preprint arXiv:2011.09410},
year = {2022}
}