The Computational Gauntlet of Human-like Learning
Abstract
In this paper, I pose a major challenge for AI researchers: to develop systems that learn in a human-like manner. I briefly review the history of machine learning, noting that early work made close contact with results from cognitive psychology but that this is no longer the case. I identify seven characteristics of human behavior that, if reproduced, would offer better ways to acquire expertise than statistical induction over massive training sets. I illustrate these points with two domains - mathematics and driving - where people are effective learners and review systems that address them. In closing, I suggest ways to encourage more research on human-like learning.
Cite
Text
Langley. "The Computational Gauntlet of Human-like Learning." AAAI Conference on Artificial Intelligence, 2022. doi:10.1609/AAAI.V36I11.21489Markdown
[Langley. "The Computational Gauntlet of Human-like Learning." AAAI Conference on Artificial Intelligence, 2022.](https://mlanthology.org/aaai/2022/langley2022aaai-computational/) doi:10.1609/AAAI.V36I11.21489BibTeX
@inproceedings{langley2022aaai-computational,
title = {{The Computational Gauntlet of Human-like Learning}},
author = {Langley, Pat},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2022},
pages = {12268-12273},
doi = {10.1609/AAAI.V36I11.21489},
url = {https://mlanthology.org/aaai/2022/langley2022aaai-computational/}
}