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.V36I11.21489

Markdown

[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.V36I11.21489

BibTeX

@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/}
}