Back
Doing More with Less: Meta-Reasoning and Meta-Learning in Humans and Machines
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.
@article{GriffithsEtAl2019, title = {Doing More with Less: Meta-Reasoning and Meta-Learning in Humans and Machines}, journal = {Current Opinion in Behavioral Sciences}, abstract = {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.}, volume = {29}, pages = {24--30}, month = oct, year = {2019}, slug = {griffithsetal2019}, author = {Griffiths, Thomas L. and Callaway, Frederick and Chang, Michael B. and Grant, Erin and Krueger, Paul M. and Lieder, Falk}, month_numeric = {10} }