Abstract
Handwritten characters drawn by a modelNot only do children learn effortlessly, they do so quickly and with a remarkable ability to use what they have learned as the raw material for creating new stuff. Lakeet al.describe a computational model that learns in a similar fashion and does so better than current deep learning algorithms. The model classifies, parses, and recreates handwritten characters, and can generate new letters of the alphabet that look “right” as judged by Turing-like tests of the model's output in comparison to what real humans produce.Science, this issue p.1332
References
80
Referenced
1,591
10.1016/0885-2014(88)90014-7
- E. M. Markman Categorization and Naming in Children (MIT Press Cambridge MA 1989).
10.1037/0033-295X.114.2.245
10.1162/neco.1992.4.1.1
10.1109/5.726791
10.1109/MSP.2012.2205597
- Krizhevsky A., Sutskever I., Hinton G. E., Adv. Neural Inf. Process. Syst. 25, 1097–1105 (2012). / Adv. Neural Inf. Process. Syst. by Krizhevsky A. (2012)
10.1038/nature14539
10.1038/nature14236
10.1006/jmps.1997.1154
10.1037/0033-295X.94.2.115
10.1006/cogp.1994.1010
10.1016/j.cogpsych.2012.09.003
10.1145/1968.1972
-
D. McAllester in Proceedings of the 11th Annual Conference on Computational Learning Theory (COLT) Madison WI 24 to 26 July 1998 (Association for Computing Machinery New York 1998) pp. 230–234.
(
10.1145/279943.279989
) 10.1109/72.788640
- N. D. Goodman J. B. Tenenbaum T. Gerstenberg Concepts: New Directions E. Margolis S. Laurence Eds. (MIT Press Cambridge MA 2015).
10.1038/nature14541
- P. H. Winston The Psychology of Computer Vision P. H. Winston Ed. (McGraw-Hill New York 1975).
-
Bever T. G., Poeppel D., Biolinguistics 4, 174 (2010).
(
10.5964/bioling.8783
) / Biolinguistics by Bever T. G. (2010) 10.1111/1467-9280.00403
- R. L. Goldstone in Perceptual Organization in Vision: Behavioral and Neural Perspectives R. Kimchi M. Behrmann C. Olson Eds. (Lawrence Erlbaum City NJ 2003) pp. 233–278.
10.1037/h0062474
10.1016/j.bbr.2009.08.031
10.1111/j.1467-7687.2007.00585.x
- R. Salakhutdinov J. Tenenbaum A. Torralba in JMLR Workshop and Conference Proceedings vol. 27 Unsupervised and Transfer Learning Workshop I. Guyon G. Dror V. Lemaire G. Taylor D. Silver Eds. (Microtome Brookline MA 2012) pp. 195–206.
10.1613/jair.731
10.1162/neco.1989.1.4.541
10.1109/TPAMI.2012.269
- Mansinghka V. K., Kulkarni T. D., Perov Y. N., Tenenbaum J. B., Adv. Neural Inf. Process. Syst. 26, 1520–1528 (2013). / Adv. Neural Inf. Process. Syst. by Mansinghka V. K. (2013)
10.1109/34.799914
- M.-P. Dubuisson A. K. Jain in Proceedings of the 12th IAPR International Conference on Pattern Recognition Vol. 1 Conference A: Computer Vision and Image Processing Jerusalem Israel 9 to 13 October 1994 (IEEE New York 1994) pp. 566–568.
- G. Koch R. S. Zemel R. Salakhutdinov paper presented at ICML Deep Learning Workshop Lille France 10 and 11 July 2015.
10.1109/34.506410
- Hinton G. E., Nair V., Adv. Neural Inf. Process. Syst. 19, 515–522 (2006). / Adv. Neural Inf. Process. Syst. by Hinton G. E. (2006)
10.1561/0600000018
- P. Liang M. I. Jordan D. Klein in Proceedings of the 27th International Conference on Machine Learning Haifa Israel 21 to 25 June 2010 (International Machine Learning Society Princeton NJ 2010) pp. 639–646.
10.1109/TPAMI.2009.167
- I. Hwang A. Stuhlm¨ller N. D. Goodman (2011) http://arxiv.org/abs/1110.5667.
- E. Dechter J. Malmaud R. P. Adams J. B. Tenenbaum in Proceedings of the 23rd International Joint Conference on Artificial Intelligence F. Rossi Ed. Beijing China 3 to 9 August 2013 (AAAI Press/International Joint Conferences on Artificial Intelligence Menlo Park CA 2013) pp. 1302–1309.
- J. Rule E. Dechter J. B. Tenenbaum in Proceedings of the 37th Annual Conference of the Cognitive Science Society D. C. Noelle et al . Eds. Pasadena CA 22 to 25 July 2015 (Cognitive Science Society Austin TX 2015) pp. 2051–2056.
10.3758/BF03196968
10.1111/j.1551-6709.2010.01113.x
10.1037/0096-3445.127.4.331
10.1016/0010-0277(81)90013-5
10.1016/j.cognition.2011.11.005
-
G. A. Miller P. N. Johnson-Laird Language and Perception (Belknap Cambridge MA 1976).
(
10.4159/harvard.9780674421288
) - T. D. Ullman A. Stuhlmuller N. Goodman J. B. Tenenbaum in Proceedings of the 36th Annual Conference of the Cognitive Science Society Quebec City Canada 23 to 26 July 2014 (Cognitive Science Society Austin TX 2014) pp. 1640–1645.
- B. M. Lake C.-y. Lee J. R. Glass J. B. Tenenbaum in Proceedings of the 36th Annual Conference of the Cognitive Science Society Quebec City Canada 23 to 26 July 2014 (Cognitive Science Society Austin TX 2014) pp. 803–808.
- U. Neisser Cognitive Psychology (Appleton-Century-Crofts New York 1966).
-
R. Treiman B. Kessler How Children Learn to Write Words (Oxford Univ. Press New York 2014).
(
10.1093/acprof:oso/9780199907977.001.0001
) 10.1111/j.1467-8624.2009.01408.x
10.1037/a0021336
- S. Dehaene Reading in the Brain (Penguin New York 2009).
10.2307/1422797
10.1016/S1053-8119(03)00088-0
10.1016/j.neuropsychologia.2006.06.026
10.1037/a0015836
10.1126/science.1225266
- A. Graves (2014) http://arxiv.org/abs/1308.0850.
- K. Gregor I. Danihelka A. Graves D. J. Rezende D. Wierstra in Proceedings of the International Conference on Machine Learning (ICML) Lille France 6 to 11 July 2015 (International Machine Learning Society Princeton NJ 2015) pp. 1462–1471.
- Chung J., et al.., Adv. Neural Inf. Process. Syst. 28, (2015). / Adv. Neural Inf. Process. Syst. by Chung J. (2015)
10.1016/0010-0285(73)90005-4
- B. M. Lake R. Salakhutdinov J. B. Tenenbaum paper presented at the 34th Annual Conference of the Cognitive Science Society Sapporo Japan 1 to 4 August 2012.
- B. M. Lake R. Salakhutdinov J. B. Tenenbaum paper presented at the Advances in Neural Information Processing Systems 26 City Country Dates Month Year.
10.1080/03640210701802071
-
T. D. Kulkarni P. Kohli J. B. Tenenbaum V. Mansinghka in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Boston MA 7 to 12 Jule 2015 (IEEE New York 2015) pp. 4390–4399.
(
10.1109/CVPR.2015.7299068
) 10.1109/34.161346
10.1016/0031-3203(90)90068-V
- B. M. Lake thesis MIT Cambridge MA (2014).
- O. Russakovsky et al . ImageNet large scale visual recognition challenge (2014) http://arxiv.org/abs/1409.0575.
-
Y. Jia et al . “Caffe: Convolutional Architecture for Fast Feature Embedding ” in Proceedings of the 22nd Annual ACM International Conference on Multimedia Orlando FL 3 to 7 November 2014 (ACM New York 2014) pp. 675–678.
(
10.1145/2647868.2654889
) - Srivastava N., Hinton G., Krizhevsky A., Sutskever I., Salakhutdinov R., Dropout: A simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014). / J. Mach. Learn. Res. / Dropout: A simple way to prevent neural networks from overfitting by Srivastava N. (2014)
-
S. Chopra R. Hadsell Y. LeCun “Learning a similarity metric discriminatively with application to face verification ” in 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) San Diego CA 20 to 26 June 2005 (IEEE New York 2005) vol. 1 pp. 539–546.
(
10.1109/CVPR.2005.202
) 10.1371/journal.pone.0057410
10.1016/0010-0277(84)90022-2
10.1214/aos/1176342360
- Sethuraman J., A constructive definition of dirichlet priors. Stat. Sin. 3, 639–650 (1994). / Stat. Sin. / A constructive definition of dirichlet priors by Sethuraman J. (1994)
- N. D. Goodman V. K. Mansinghka D. M. Roy K. Bonawitz J. B. Tenenbaum “Church: A language for generative models ” in Uncertainty in Artificial Intelligence (2008) pp. 220–229.
- T. J. O’Donnell thesis Harvard University Cambridge MA (2011).
Dates
Type | When |
---|---|
Created | 9 years, 8 months ago (Dec. 13, 2015, 1:05 a.m.) |
Deposited | 2 months, 3 weeks ago (May 31, 2025, 3:31 p.m.) |
Indexed | 9 hours, 42 minutes ago (Aug. 24, 2025, 6:54 p.m.) |
Issued | 9 years, 8 months ago (Dec. 11, 2015) |
Published | 9 years, 8 months ago (Dec. 11, 2015) |
Published Print | 9 years, 8 months ago (Dec. 11, 2015) |
Funders
6
Office of Naval Research
10.13039/100000006
Region: Americas
gov (National government)
Labels
6
- U.S. Office of Naval Research
- Naval Research
- United States Office of Naval Research
- U.S. Department of the Navy Office of Naval Research
- The Office of Naval Research
- ONR
Awards
3
- N000141310333
- W911NF-08-1-0242
- W911NF-13-1-2012
Army Research Office
10.13039/100000183
Region: Americas
gov (National government)
Labels
5
- U.S. Army Research Office
- United States Army Research Office
- U.S. Army Research Laboratory's Army Research Office
- ARL's Army Research Office
- ARO
Canadian Institute for Advanced Research
10.13039/100007631
Region: Americas
gov (Research institutes and centers)
Labels
5
- L'Institut Canadien de Recherches Avancées
- Institut Canadien de Recherches Avancées
- The Canadian Institute for Advanced Research
- CIFAR
- ICRA
Natural Sciences and Engineering Research Council of Canada
10.13039/501100000038
Region: Americas
gov (National government)
Labels
3
- Conseil de Recherches en Sciences Naturelles et en Génie du Canada
- NSERC
- CRSNG
NSF Science and Technology Center
Awards
1
- CCF-1231216
Moore-Sloan Data Science Environment at NYU
@article{Lake_2015, title={Human-level concept learning through probabilistic program induction}, volume={350}, ISSN={1095-9203}, url={http://dx.doi.org/10.1126/science.aab3050}, DOI={10.1126/science.aab3050}, number={6266}, journal={Science}, publisher={American Association for the Advancement of Science (AAAS)}, author={Lake, Brenden M. and Salakhutdinov, Ruslan and Tenenbaum, Joshua B.}, year={2015}, month=dec, pages={1332–1338} }