Format

Send to

Choose Destination
Behav Brain Sci. 2017 Jan;40:e253. doi: 10.1017/S0140525X16001837. Epub 2016 Nov 24.

Building machines that learn and think like people.

Author information

1
Department of Psychology and Center for Data Science,New York University,New York,NY 10011brenden@nyu.eduhttp://cims.nyu.edu/~brenden/.
2
Department of Brain and Cognitive Sciences and The Center for Brains,Minds and Machines,Massachusetts Institute of Technology,Cambridge,MA 02139tomeru@mit.eduhttp://www.mit.edu/~tomeru/.
3
Department of Brain and Cognitive Sciences and The Center for Brains,Minds and Machines,Massachusetts Institute of Technology,Cambridge,MA 02139jbt@mit.eduhttp://web.mit.edu/cocosci/josh.html.
4
Department of Psychology and Center for Brain Science,Harvard University,Cambridge,MA 02138, andThe Center for Brains, Minds and Machines,Massachusetts Institute of Technology,Cambridge,MA 02139gershman@fas.harvard.eduhttp://gershmanlab.webfactional.com/index.html.

Abstract

Recent progress in artificial intelligence has renewed interest in building systems that learn and think like people. Many advances have come from using deep neural networks trained end-to-end in tasks such as object recognition, video games, and board games, achieving performance that equals or even beats that of humans in some respects. Despite their biological inspiration and performance achievements, these systems differ from human intelligence in crucial ways. We review progress in cognitive science suggesting that truly human-like learning and thinking machines will have to reach beyond current engineering trends in both what they learn and how they learn it. Specifically, we argue that these machines should (1) build causal models of the world that support explanation and understanding, rather than merely solving pattern recognition problems; (2) ground learning in intuitive theories of physics and psychology to support and enrich the knowledge that is learned; and (3) harness compositionality and learning-to-learn to rapidly acquire and generalize knowledge to new tasks and situations. We suggest concrete challenges and promising routes toward these goals that can combine the strengths of recent neural network advances with more structured cognitive models.

Comment in

PMID:
27881212
DOI:
10.1017/S0140525X16001837
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Cambridge University Press
Loading ...
Support Center