The Omniglot challenge: a 3-year progress report
Name
1902.03477.pdf
Description
Accepted version
Size
1.46 MB
Format
Adobe PDF
Checksum (MD5)
bd025355ea7e0a18bc09bd339c1ec6d8
Author(s)
Tenenbaum, Joshua B
Date Issued
October 2019
Journal
Current Opinion in Behavioral Sciences
Publisher
Elsevier BV
Citation
Lake, Brenden M., Ruslan Salakhutdinov, and Joshua B. Tenenbaum. “The Omniglot challenge: a 3-year progress report.” Current Opinion in Behavioral Sciences, vol. 29, 2019, pp. 97-102 © 2019 The Author(s)
Version
Author's final manuscript
Abstract
Three years ago, we released the Omniglot dataset for one-shot learning, along with five challenge tasks and a computational model that addresses these tasks. The model was not meant to be the final word on Omniglot; we hoped that the community would build on our work and develop new approaches. In the time since, we have been pleased to see wide adoption of the dataset. There has been notable progress on one-shot classification, but researchers have adopted new splits and procedures that make the task easier. There has been less progress on the other four tasks. We conclude that recent approaches are still far from human-like concept learning on Omniglot, a challenge that requires performing many tasks with a single model.
MIT Department
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Terms of Use
Creative Commons Attribution-NonCommercial-NoDerivs License
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1016/j.cobeha.2019.04.007
