Cite as: D. George et al., Science 10.1126/science.aag2612 (2017). RESEARCH ARTICLES First release: 26 October 2017 www.sciencemag.org (Page numbers not final at time of first release) 1
The ability to learn and generalize from a few examples is a hallmark of human intelligence (1). CAPTCHAs, images used by websites to block automated interactions, are examples of problems that are easy for humans but difficult for comput- ers. CAPTCHAs are hard for algorithms because they add clutter and crowd letters together to create a chicken-and-egg problem for character classifiers — the classifiers work well for characters that have been segmented out, but segmenting the individual characters requires an understanding of the characters, each of which might be rendered in a combinato- rial number of ways (2–5). A recent deep-learning approach for parsing one specific CAPTCHA style required millions of labeled examples from it (6), and earlie
