Doing More with Less: Meta-Reasoning and Meta-Learning in Humans and Machines
2019
Article
re
Artificial intelligence systems use an increasing amount of computation and data to solve very specific problems. By contrast, human minds solve a wide range of problems using a fixed amount of computation and limited experience. We identify two abilities that we see as crucial to this kind of general intelligence: meta-reasoning (deciding how to allocate computational resources) and meta-learning (modeling the learning environment to make better use of limited data). We summarize the relevant AI literature and relate the resulting ideas to recent work in psychology.
| Author(s): | Thomas L. Griffiths and Frederick Callaway and Michael B. Chang and Erin Grant and Paul M. Krueger and Falk Lieder |
| Journal: | Current Opinion in Behavioral Sciences |
| Volume: | 29 |
| Pages: | 24--30 |
| Year: | 2019 |
| Month: | October |
| Department(s): | Rationality Enhancement |
| Research Project(s): |
Metacognitive Learning
|
| Bibtex Type: | Article (article) |
| Paper Type: | Journal |
| DOI: | 10.1016/j.cobeha.2019.01.005 |
| Language: | English |
| State: | Published |
|
BibTex @article{GriffithsEtAl2019,
title = {Doing More with Less: Meta-Reasoning and Meta-Learning in Humans and Machines},
author = {Griffiths, Thomas L. and Callaway, Frederick and Chang, Michael B. and Grant, Erin and Krueger, Paul M. and Lieder, Falk},
journal = {Current Opinion in Behavioral Sciences},
volume = {29},
pages = {24--30},
month = oct,
year = {2019},
doi = {10.1016/j.cobeha.2019.01.005},
month_numeric = {10}
}
|
|
