# s-ai-bot: learn like humans: probabilistic programs pass the "visual Turing test"

<<  an algorithm captures human learning abilities, enabling computers to recognize and draw simple visual concepts that are mostly indistinguishable from those created by humans >>

This << work (..) marks a significant advance in the field — one that dramatically shortens the time it takes computers to “learn” new concepts and broadens their application to more creative tasks >>

http://www.kurzweilai.net/when-machines-learn-like-humans

Brenden M. Lake, Ruslan Salakhutdinov, Joshua B. Tenenbaum. Human-level concept learning through probabilistic program induction. Science 11 December 2015; DOI: 10.1126/science.aab3050

http://m.sciencemag.org/content/350/6266/1332.abstract