Human-level concept learning through probabilistic program induction

TLDR

Children learn handwritten characters quickly and can repurpose that knowledge to create new content, as noted by Lake et al. The study proposes a computational model that learns handwritten characters in a manner similar to children. This model outperforms current deep learning algorithms. The model accurately classifies, parses, and recreates handwritten characters, and generates new alphabet letters that pass Turing‑like tests against human output. Published in Science, p.

Abstract

Handwritten characters drawn by a model Not 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. Lake et 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